{"title":"All products","description":null,"products":[{"product_id":"iphone-17-pro-max","title":"Apple iPhone 17 Pro Max (12 GB, 2 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003e12 GB and Apple's fastest on-device AI of 2025.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 12 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e A19 Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e iOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e6.9-inch flagship phone featuring the Apple A19 Pro chip with a 6-core CPU, 6-core GPU, and 16-core Neural Engine, 12 GB of memory, up to 2 TB of storage, a 120 Hz ProMotion Super Retina XDR display, and a 48 MP triple camera system with 8× optical-quality zoom.\u003c\/p\u003e\u003cp\u003eDesigned as an always-on personal endpoint for the One runtime, with on-device Apple Intelligence, Core ML and MLX for local models, Apple's Foundation Models framework for developers, and the same silicon lineage as the M-series so models trained on a Mac run unchanged.\u003c\/p\u003e\u003cp\u003eFits in a pocket with all-day battery, USB-C 3 at 10 Gb\/s, Face ID and Secure Enclave for private inference, and the ability to run a 3-billion-parameter model on device with headroom for the operating system.\u003c\/p\u003e\u003cp\u003e$1,199. No cash discount at launch; carrier credits only.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419570630872,"sku":"APL-IP17PM","price":1199.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470515249368.jpg?v=1791848867"},{"product_id":"ipad-pro-m5","title":"Apple iPad Pro M5 (16 GB, 2 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eM5 and 16 GB make it the most capable tablet for on-device AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e iPadOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e11-inch or 13-inch tablet featuring the Apple M5 chip with a 10-core CPU, 10-core GPU with Neural Accelerators, and 16-core Neural Engine, 12 GB or 16 GB of memory, up to 2 TB of storage, and an Ultra Retina XDR tandem OLED display at 120 Hz.\u003c\/p\u003e\n\u003cp\u003eDesigned as a portable endpoint for the One runtime, with on-device Apple Intelligence, Core ML and MLX for local models, Thunderbolt 4 for external displays and storage, and Apple Pencil Pro and Magic Keyboard support.\u003c\/p\u003e\n\u003cp\u003eWeighs from 444 g with all-day battery, Face ID and Secure Enclave, and the ability to run a 7-billion-parameter model at 4-bit on the 16 GB configuration.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419580199128,"sku":"APL-IPADPRO-M5","price":1199.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470521409752.jpg?v=1791848867"},{"product_id":"ipad-air-m3","title":"Apple iPad Air M3 (8 GB, 1 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA great big-screen Hussh One app; limited room for on-device models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App only\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 8 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M3\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e iPadOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e11-inch or 13-inch tablet featuring the Apple M3 chip with an 8-core CPU, 9-core GPU, and 16-core Neural Engine, 8 GB of memory, up to 1 TB of storage, and a Liquid Retina display.\u003c\/p\u003e\n\u003cp\u003eDesigned as a portable endpoint for the One runtime, with on-device Apple Intelligence, Core ML for local models, USB-C 3 at 10 Gb\/s, and Apple Pencil Pro and Magic Keyboard support.\u003c\/p\u003e\n\u003cp\u003eWeighs from 460 g with all-day battery, Touch ID and Secure Enclave, and the ability to run a 3-billion-parameter model on device.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419580887256,"sku":"APL-IPADAIR-M3","price":749.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470522196184.jpg?v=1791848867"},{"product_id":"mac-mini-m4","title":"Apple Mac mini M4 (32 GB, 2 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Entry\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 32 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M4\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\u003c\/div\u003e\u003cp\u003e5-inch square desktop featuring the Apple M4 chip with a 10-core CPU, 10-core GPU, and 16-core Neural Engine, 16 GB to 32 GB of unified memory at 120 GB\/s, up to 2 TB of SSD storage, and Thunderbolt 4.\u003c\/p\u003e\u003cp\u003eDesigned for always-on local inference and agent runtimes, with macOS, Core ML, and Apple's MLX framework for running open-weight models, and Xcode for developers.\u003c\/p\u003e\u003cp\u003eSits on a desk at 0.7 kg, silent at idle and under 65 W at load from a single power cord, with Gigabit Ethernet and Wi-Fi 6E, and the ability to run a 13-billion-parameter model at 4-bit on the 32 GB configuration.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419657138392,"sku":"APL-MACMINI-M4","price":799.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470566596824.jpg?v=1791848868"},{"product_id":"mac-mini-m4-pro","title":"Apple Mac mini M4 Pro (64 GB, 8 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 64 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M4 Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\u003c\/div\u003e\u003cp\u003e5-inch square desktop featuring the Apple M4 Pro chip with up to a 14-core CPU, 20-core GPU, and 16-core Neural Engine, 24 GB to 64 GB of unified memory at 273 GB\/s, up to 8 TB of SSD storage, and Thunderbolt 5 at 120 Gb\/s.\u003c\/p\u003e\u003cp\u003eDesigned for always-on local inference on models that exceed consumer VRAM, with macOS, Core ML, and MLX for open-weight models, and 10 Gigabit Ethernet as an option for serving on a local network.\u003c\/p\u003e\u003cp\u003eSits on a desk at 0.7 kg, silent at idle and under 140 W at load, and runs a 32-billion-parameter model at 8-bit or a 70-billion-parameter model at 4-bit on the 64 GB configuration.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419659890904,"sku":"APL-MACMINI-M4PRO","price":1599.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470569316568.jpg?v=1791848868"},{"product_id":"mac-studio-m3-ultra-96gb","title":"Apple Mac Studio M3 Ultra (512 GB, 16 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Frontier\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 512 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M3 Ultra\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\u003c\/div\u003e\u003cp\u003eCompact desktop workstation built on the Apple M3 Ultra, with up to a 32-core CPU, an 80-core GPU, a 32-core Neural Engine, 96 GB to 512 GB of unified memory at 819 GB\/s, up to 16 TB of internal SSD, and six Thunderbolt 5 ports.\u003c\/p\u003e\u003cp\u003eDesigned for local inference through Apple's MLX framework and Metal, with macOS, Xcode, and Core ML included, 10 Gigabit Ethernet for serving on a local network, and configurable to 512 GB of unified memory for the largest open-weight models.\u003c\/p\u003e\u003cp\u003eSilent under sustained load at 3.6 kg, powered from a single cord at under 480 W, and runs a 70-billion-parameter model at 8-bit at 96 GB, or a 671-billion-parameter model quantized at 512 GB.\u003c\/p\u003e\u003cp\u003e$5,299 (96 GB, 1 TB) after Apple's June 25 repricing; 13–14 week lead time. The 512 GB configuration is ~$9,500 and capped by the DRAM cycle.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419666673880,"sku":"APL-MACSTUDIO-M3ULTRA","price":5299.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470575804632.jpg?v=1791848868"},{"product_id":"mac-studio-m5-ultra","title":"Apple Mac Studio M5 Ultra (512 GB, 1 TB)","description":"\u003cdiv class=\"hushh-quote-enquiry\" data-version=\"1\"\u003e\u003cp\u003e\u003cstrong\u003ePricing and availability on request.\u003c\/strong\u003e \u003ca href=\"mailto:support@hushh.ai?subject=Quote%20request%3A%20Apple%20Mac%20Studio%20M5%20Ultra%20(512%20GB%2C%201%20TB)\"\u003eEmail support@hushh.ai to request a quote\u003c\/a\u003e. Please include the product name and delivery ZIP code. We will confirm the configuration, final price, and availability before accepting an order.\u003c\/p\u003e\u003c\/div\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-10-12\"\u003e\n\u003cp\u003e\u003cstrong\u003eRun frontier-size open models entirely at home, with 512 GB of unified memory.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Frontier\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 512 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Ultra (36-core CPU, 80-core GPU)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e 512 GB configuration not yet orderable; Apple says late October 2026\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eMac Studio with M5 Ultra is shipping from $5,499 (96 GB, 1 TB). The 512 GB memory option requires the 36-core CPU \/ 80-core GPU chip and starts at 1 TB of storage. Apple hasn't published its price yet; the 256 GB configuration is $10,799.\u003c\/p\u003e\u003cp\u003eJoin the list and we'll confirm price and delivery as soon as Apple opens orders.\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.apple.com\/mac-studio\/specs\/\" target=\"_blank\" rel=\"noopener\"\u003eApple\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Request information","offer_id":52551970029784,"sku":"APL-MACSTUDIO-M5ULTRA","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470575837400.jpg?v=1791848868"},{"product_id":"google-pixel-10-pro","title":"Google Pixel 10 Pro (16 GB, 1 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eGoogle's own AI phone, with Gemini Nano on device and 16 GB.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Tensor G5\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Android\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e6.3-inch flagship phone featuring the Google Tensor G5 with a dedicated TPU, 16 GB of memory, up to 1 TB of storage, a 120 Hz LTPO Super Actua display, and a 50 MP triple camera system with a 5× periscope telephoto.\u003c\/p\u003e\u003cp\u003eDesigned as an always-on personal endpoint for the One runtime, with Gemini Nano running on device, the Titan M2 security chip, Google AI Edge and LiteRT for developer models, and seven years of OS and security updates.\u003c\/p\u003e\u003cp\u003eFits in a pocket with all-day battery and Qi2 wireless charging, USB-C 3.2, and the ability to run a 7-billion-parameter model at 4-bit in 16 GB of memory.\u003c\/p\u003e\u003cp\u003e$699 (128 GB); lowest seen $684 (Prime Day). Pixel 11 launched August 12, 2026 — expect clearance.\u003c\/p\u003e","brand":"Google","offers":[{"title":"Default Title","offer_id":52419699769560,"sku":"GOO-P10P","price":699.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470602412248.jpg?v=1791848868"},{"product_id":"nvidia-jetson-orin-nano-super","title":"NVIDIA Jetson Orin Nano Super (8 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eLow-cost edge AI for small models and sensors.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Below minimum\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 8 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA Jetson Orin Nano\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e JetPack (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Can't hold the default model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003ePalm-sized edge AI developer kit featuring the NVIDIA Jetson Orin Nano Super module with a 6-core Arm Cortex-A78AE CPU, a 1,024-core Ampere GPU with 32 Tensor Cores, 8 GB of LPDDR5 memory at 102 GB\/s, and delivering up to 67 TOPS of INT8 AI performance.\u003c\/p\u003e\u003cp\u003eDesigned for robotics, vision, and small-model inference at the edge, with JetPack 6 on Ubuntu, CUDA, TensorRT, and the NVIDIA Isaac and Metropolis SDKs preinstalled, and support for PyTorch, Ollama, and Jetson Generative AI Lab.\u003c\/p\u003e\u003cp\u003eFits in a pocket on a reference carrier board with four USB 3.2 ports, Gigabit Ethernet, a microSD slot and M.2 slots, draws 7 to 25 W, and runs a 3-billion-parameter model at 4-bit or an 8-billion-parameter model quantized with limited context.\u003c\/p\u003e\u003cp\u003e$249. NVIDIA fixed price; in stock.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":52419709927640,"sku":"NV-JETSON-ONS","price":249.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470612242648.jpg?v=1791848868"},{"product_id":"jetson-agx-orin-64gb","title":"NVIDIA Jetson AGX Orin Developer Kit (64 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA rugged 64 GB edge computer for robotics and field AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Unverified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 64 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA Jetson AGX Orin\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e JetPack (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e LM Studio not confirmed on Jetson\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eEdge AI developer kit featuring the NVIDIA Jetson AGX Orin module with a 12-core Arm Cortex-A78AE CPU, a 2,048-core Ampere GPU with 64 Tensor Cores, two NVDLA accelerators, 64 GB of LPDDR5 memory at 204.8 GB\/s, 64 GB of eMMC, and delivering up to 275 TOPS of INT8 AI performance.\u003c\/p\u003e\n\u003cp\u003eDesigned for robotics, autonomous machines, and multi-model inference at the edge, with JetPack 6 on Ubuntu, CUDA, TensorRT, DeepStream, and the Isaac SDK preinstalled, and support for PyTorch and Ollama for language models.\u003c\/p\u003e\n\u003cp\u003eFits on a desk or in a vehicle at 110 × 110 mm, with 10 GbE, USB-C, PCIe Gen4 M.2 slots and a 40-pin header, configurable from 15 to 60 W, and runs a 32-billion-parameter model at 8-bit or a 70-billion-parameter model at 4-bit in 64 GB of memory.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":52419723034840,"sku":"NV-JETSON-AGXORIN64","price":1999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470622433496.jpg?v=1791848869"},{"product_id":"dell-pro-max-16-rtx-pro","title":"Dell Pro Max 16 (RTX PRO 5000 24 GB, 128 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA pro workstation laptop; the model fits entirely on its 24 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX PRO 5000 Blackwell (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e16-inch mobile workstation featuring an Intel Core Ultra 9 285HX processor with vPro, an NVIDIA RTX PRO 5000 Blackwell GPU with 24 GB of GDDR7 on a replaceable module, up to 128 GB of DDR5-6400 CAMM2 memory, up to 8 TB across two PCIe Gen5 SSDs, and a 16-inch QHD+ 120 Hz display.\u003c\/p\u003e\u003cp\u003eDesigned for local inference, fine-tuning, and rendering on a certified professional GPU, with Windows 11 Pro, NVIDIA AI Enterprise and CUDA support, Intel OpenVINO across the iGPU and NPU, Thunderbolt 5, and Dell's DGFF graphics module that allows the GPU to be serviced or upgraded.\u003c\/p\u003e\u003cp\u003eCarries at roughly 2.9 kg with a bottom hatch for user-serviceable memory and storage, ISV certifications and enterprise manageability, and the ability to run a 32-billion-parameter model at 4-bit in GPU memory or larger models by spilling into system RAM.\u003c\/p\u003e\u003cp\u003eFrom ~$4,100 with integrated graphics; the RTX PRO 5000 is a ~$3,560 upgrade. Dell configurator pricing.\u003c\/p\u003e","brand":"Dell","offers":[{"title":"Default Title","offer_id":52419723067608,"sku":"DELL-MB16250","price":4109.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470622466264.jpg?v=1791848869"},{"product_id":"hp-zbook-fury-g1i-18-rtx-pro-5000","title":"HP ZBook Fury G1i 18 (RTX PRO 5000 24 GB, 192 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA top-spec mobile workstation for heavy local AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU + 192 GB RAM\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX PRO 5000 Blackwell (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e18-inch desktop-replacement mobile workstation featuring an Intel Core Ultra 9 285HX processor with vPro, an NVIDIA RTX PRO 5000 Blackwell GPU with 24 GB of GDDR7 at up to 175 W, up to 192 GB of DDR5 memory across four SODIMM slots, up to 16 TB across four PCIe Gen5 SSDs with RAID, and an 18-inch 4K 120 Hz display.\u003c\/p\u003e\u003cp\u003eDesigned for local inference, fine-tuning, and rendering on a certified professional GPU, with Windows 11 Pro or Ubuntu, NVIDIA AI Enterprise and CUDA support, Intel OpenVINO across the iGPU and NPU, Thunderbolt 5, and HP Wolf Security with ISV certifications.\u003c\/p\u003e\u003cp\u003eCarries at roughly 3.6 kg with a tool-less service door for memory and storage, a 99 Wh battery and a 330 W adapter, and runs a 32-billion-parameter model at 4-bit in GPU memory or a 70-billion-parameter model at 4-bit by spilling into 192 GB of system RAM.\u003c\/p\u003e\u003cp\u003eFrom ~$8,000 with the RTX PRO 5000. HP configurator pricing; the 192 GB memory ceiling is the reason to pick it over the Dell.\u003c\/p\u003e","brand":"HP","offers":[{"title":"Default Title","offer_id":52419723985112,"sku":"HP-ZBOOKFURY-G1I-18","price":8000.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470623383768.jpg?v=1791848869"},{"product_id":"nvidia-dgx-spark","title":"NVIDIA DGX Spark (128 GB, 4 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-10-12\"\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA's own desktop agent computer, built to run local agents 24\/7.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA GB10 Grace Blackwell\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e DGX OS (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux ARM64 (LM Studio officially supports GB10)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Limited; NVIDIA's own store is sold out\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eDesktop AI system built on the NVIDIA GB10 Grace Blackwell Superchip, with 128 GB of unified LPDDR5X memory, a 20-core Arm CPU, 4 TB of NVMe storage, and up to 1 PFLOPS of FP4 AI performance in a 150 mm square chassis.\u003c\/p\u003e\u003cp\u003eDesigned to run and fine-tune models locally at full precision, with DGX OS, NVIDIA's AI software stack, CUDA, and Ollama preinstalled, and the same containers that run on DGX Cloud. Two units link over ConnectX-7 at 200 Gb\/s to pool 256 GB of memory.\u003c\/p\u003e\u003cp\u003eDraws under 240 W from a standard wall outlet, with Wi-Fi 7, 10 GbE, and four USB-C ports, runs models up to 200 billion parameters on a single unit, and up to 405 billion on a linked pair.\u003c\/p\u003e\u003cp\u003e$6,950 Founders Edition (NVIDIA list price since October 2, 2026).\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":52419725164760,"sku":"NV-DGX-SPARK","price":6950.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470623973592.jpg?v=1791848416"},{"product_id":"dual-dgx-spark-linked","title":"NVIDIA Dual DGX Spark, linked (2× 128 GB, 2× 4 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eTwo Sparks for running more agents or models side by side.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro (with caveat)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 2x 128 GB (not one pool for LM Studio)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e 2x NVIDIA GB10\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e DGX OS (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux ARM64 (LM Studio officially supports GB10)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e LM Studio runs a model on one machine, so the pair does not act as 256 GB for Puppy One.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eTwo NVIDIA DGX Spark systems linked over their built-in ConnectX-7 SmartNICs at 200 Gb\/s, each with 128 GB of unified LPDDR5X memory (2× 128 GB), 40 Arm CPU cores, 8 TB of NVMe storage, and up to 2 PFLOPS of FP4 AI performance across two 150 mm square chassis.\u003c\/p\u003e\n\u003cp\u003eDesigned to run and fine-tune models that exceed a single unit's memory, with DGX OS, NVIDIA's AI software stack, CUDA, and NCCL for multi-node inference preinstalled, and the same containers that run on DGX Cloud.\u003c\/p\u003e\n\u003cp\u003eSits on one desk drawing under 480 W from two standard outlets, with a single 400G QSFP112 direct-attach cable between the units, and runs models up to 405 billion parameters at FP4 across the pair.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":52419729490136,"sku":"NV-DGX-SPARK-X2","price":9398.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470627676376.jpg?v=1791848869"},{"product_id":"rtx-pro-5000-72gb-tower","title":"RTX PRO 5000 Tower (72 GB, 256 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA 72 GB GPU for large models at full speed.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 72 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX PRO 5000 Blackwell 72 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux \/ Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eFull-size desktop workstation built around a single NVIDIA RTX PRO 5000 Blackwell with 72 GB of GDDR7 ECC memory delivering up to 2,900 AI TOPS at FP4, paired with an AMD Threadripper PRO or Intel Xeon W processor, up to 256 GB of DDR5 ECC memory, PCIe Gen5 NVMe storage, and a 1,000 W or larger power supply.\u003c\/p\u003e\u003cp\u003eDesigned for local inference and fine-tuning on models that exceed consumer VRAM at a lower cost than the 96 GB card, with Windows 11 Pro or Ubuntu, NVIDIA AI Enterprise, CUDA, PyTorch, and Triton support, and ISV certifications for engineering and media workflows.\u003c\/p\u003e\u003cp\u003eFloor-standing on a standard outlet at roughly 600 W under sustained load, ECC memory throughout, and the ability to run a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in GPU memory.\u003c\/p\u003e\u003cp\u003eFrom ~$10,000. The card alone lists at $9,310–9,999 (SHI, Scan); built systems from Puget, Lambda, Dell, HP, and Lenovo run $10,000–15,000.\u003c\/p\u003e","brand":"Hussh Build","offers":[{"title":"Default Title","offer_id":52419730079960,"sku":"BLD-RTXPRO5000-TOWER","price":10000.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470628200664.jpg?v=1791848869"},{"product_id":"rtx-pro-6000-blackwell-96gb-tower","title":"RTX PRO 6000 Blackwell Tower (96 GB, 256 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA 96 GB GPU tower for very large models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 96 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX PRO 6000 Blackwell\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux \/ Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eFull-size desktop workstation built around a single NVIDIA RTX PRO 6000 Blackwell Workstation Edition with 96 GB of GDDR7 ECC memory delivering up to 4,000 AI TOPS at FP4, paired with an AMD Threadripper PRO or Intel Xeon W processor, up to 256 GB of DDR5 ECC memory, PCIe Gen5 NVMe storage, and a 1,600 W power supply.\u003c\/p\u003e\u003cp\u003eDesigned for local inference and fine-tuning on the largest single-GPU memory available in a desktop, with Windows 11 Pro or Ubuntu, NVIDIA AI Enterprise, CUDA, PyTorch, and Triton support, ISV certifications, and a second PCIe x16 slot for a matching card.\u003c\/p\u003e\u003cp\u003eFloor-standing on a dedicated 15 A circuit at roughly 900 W under sustained load, ECC memory throughout, and the ability to run a 70-billion-parameter model at 8-bit or a 180-billion-parameter model at 4-bit entirely in GPU memory.\u003c\/p\u003e\u003cp\u003eFrom ~$20,000. The card alone is $16,000 on NVIDIA's marketplace as of September 2026, up 87% since launch; built systems $20,000–25,000.\u003c\/p\u003e","brand":"Hussh Build","offers":[{"title":"Default Title","offer_id":52419731259608,"sku":"BLD-RTXPRO6000-TOWER","price":20000.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470629282008.jpg?v=1791848869"},{"product_id":"dual-rtx-pro-6000-threadripper-pro","title":"Dual RTX PRO 6000 Blackwell Tower (192 GB, 512 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eFor teams running the largest open models locally.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Frontier\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 2x 96 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e 2x RTX PRO 6000 Blackwell\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux \/ Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eFull-size desktop workstation built around two NVIDIA RTX PRO 6000 Blackwell Workstation Edition GPUs with 192 GB of combined GDDR7 ECC memory delivering up to 8,000 AI TOPS at FP4, paired with an AMD Threadripper PRO 9000 WX processor with up to 96 cores, up to 512 GB of DDR5 ECC memory across eight channels, PCIe Gen5 NVMe storage, and a 2,000 W power supply.\u003c\/p\u003e\u003cp\u003eDesigned for local inference and fine-tuning on models that exceed a single GPU, with Windows 11 Pro or Ubuntu, NVIDIA AI Enterprise, CUDA, PyTorch, and Triton support, tensor parallelism across both cards over PCIe Gen5, and ISV certifications.\u003c\/p\u003e\u003cp\u003eFloor-standing on a dedicated 20 A circuit at roughly 1,600 W under sustained load, ECC memory throughout, and the ability to run a 120-billion-parameter model at 8-bit or a 405-billion-parameter model at 4-bit across both GPUs.\u003c\/p\u003e\u003cp\u003eFrom ~$40,000. Two cards alone are $32,000 at current NVIDIA pricing; built systems from Puget, Lambda Vector Pro, and Comino run $40,000–50,000.\u003c\/p\u003e","brand":"Hussh Build","offers":[{"title":"Default Title","offer_id":52419731882200,"sku":"BLD-2XRTXPRO6000-TOWER","price":40000.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470629904600.jpg?v=1791848870"},{"product_id":"dgx-b300-8-gpu-system","title":"NVIDIA DGX B300 (8× B300, 2,304 GB)","description":"\u003cdiv class=\"hushh-quote-enquiry\" data-version=\"1\"\u003e\u003cp\u003e\u003cstrong\u003ePricing and availability on request.\u003c\/strong\u003e \u003ca href=\"mailto:support@hushh.ai?subject=Quote%20request%3A%20NVIDIA%20DGX%20B300%20(8%C3%97%20B300%2C%202%2C304%20GB)\"\u003eEmail support@hushh.ai to request a quote\u003c\/a\u003e. Please include the product name and delivery ZIP code. We will confirm the configuration, final price, and availability before accepting an order.\u003c\/p\u003e\u003c\/div\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003ePrivate cloud compute for teams and enterprises.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Not Puppy One (POD \/ private cloud)\u003c\/li\u003e\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e10U rackmount AI system featuring eight NVIDIA Blackwell Ultra B300 GPUs on an HGX B300 baseboard, equipped with 2.3 TB of HBM3e memory, dual Intel Xeon 6 processors, up to 4 TB of DDR5, eight ConnectX-8 SuperNICs at 800 Gb\/s, and delivering up to 144 PFLOPS of FP4 AI performance.\u003c\/p\u003e\u003cp\u003eDesigned to train and serve trillion-parameter-class models on a single node as NVIDIA's own reference system, with fifth-generation NVLink and NVSwitch at 1.8 TB\/s between GPUs, DGX OS and NVIDIA AI Enterprise preinstalled, and Mission Control for fleet operations when scaled to SuperPOD.\u003c\/p\u003e\u003cp\u003eAir-cooled in a standard rack at roughly 14 kW of continuous draw on a three-phase feed, and able to run a 1-trillion-parameter model at FP8 or larger at FP4 entirely in GPU memory.\u003c\/p\u003e\u003cp\u003ePrice available on request. NVIDIA list has moved above $300,000; OEM 8× B200 boxes list at $490,000, so budget $500,000+.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Request a quote","offer_id":52457679519960,"sku":"NV-DGX-B300","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470631674072.jpg?v=1791848870"},{"product_id":"starlink-mini-jetson-field-node","title":"Starlink Mini + Jetson Field Node (8 GB, off-grid)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eOff-grid connectivity plus small-model edge AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Below minimum\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 8 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA Jetson + Starlink Mini\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e JetPack\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Can't hold the default model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003ePortable off-grid AI node combining a Starlink Mini terminal with built-in Wi-Fi and roughly 100 Mb\/s downlink from a laptop-sized antenna, an NVIDIA Jetson Orin Nano Super with 8 GB of LPDDR5 and 67 TOPS of INT8 performance, and a 100 Wh USB-C power bank or solar panel.\u003c\/p\u003e\u003cp\u003eDesigned for field operations, remote sensing, and robotics anywhere with a view of the sky, with JetPack, CUDA, and TensorRT on the Jetson, local inference when the link drops and cloud fallback when it returns, and the whole kit fitting in a backpack.\u003c\/p\u003e\u003cp\u003eDraws roughly 40 W for the terminal and 7 to 25 W for the Jetson, runs for hours on a power bank or indefinitely on a 100 W panel, and runs a 3-billion-parameter model at 4-bit on device.\u003c\/p\u003e\u003cp\u003e~$1,000 as a kit: Starlink Mini ($599 hardware, service from $50\/month), Jetson Orin Nano Super ($249), power bank and enclosure. Reference bill of materials; assemble yourself.\u003c\/p\u003e","brand":"Hussh Build","offers":[{"title":"Default Title","offer_id":52419746332888,"sku":"BLD-STARLINK-JETSON","price":1000.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470640259288.jpg?v=1791848871"},{"product_id":"puppy-one-max","title":"Puppy One Max","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe flagship Puppy One you can carry.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Max\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eThe flagship Puppy One tier, priced at $3,669.69. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419747414232,"sku":null,"price":3669.69,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_9b75dd38-7eaa-4b9e-9048-7b94cd5e2fa4.png?v=1790221443"},{"product_id":"puppy-one-max-pro","title":"Puppy One Max Pro","description":"\u003cdiv class=\"puppy-one-fit\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe highest-spec Puppy One: the most capable Mac laptop, with Agent One built in.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eHardware:\u003c\/strong\u003e Apple MacBook Pro 16 with M5 Max\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Max\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAgent One:\u003c\/strong\u003e Built in\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eThe ultimate Puppy One tier, priced at $8,469.69. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419747479768,"sku":null,"price":8469.69,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_ac407d2d-80e4-4e6f-8a37-54460c9e80a1.png?v=1790221400"},{"product_id":"puppy-one-32","title":"Puppy One 32","description":"\u003cp\u003e\u003cstrong\u003eHardware:\u003c\/strong\u003e Mac mini M6, 32 GB, 1 TB\u003c\/p\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe easiest way to own your AI: a small, silent Mac that runs Puppy One all day.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Entry\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 32 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M6\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eApple hardware configuration starting from $899. Verified July 7, 2026. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419748659416,"sku":null,"price":899.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_570dd195-6248-46bf-9d31-5295ed2f74c4.png?v=1790221360"},{"product_id":"puppy-one-64","title":"Puppy One 64","description":"\u003cp\u003e\u003cstrong\u003eHardware:\u003c\/strong\u003e Mac mini M5 Pro, 64 GB, 2 TB\u003c\/p\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eOur pick for most people: always on, quiet, and room for longer conversations.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 64 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eApple hardware configuration starting from $1,699. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419749675224,"sku":null,"price":1699.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_56377a2b-f737-4bb7-a2f0-18578ab2cfcd.png?v=1790221332"},{"product_id":"puppy-one-128","title":"Puppy One 128","description":"\u003cp\u003e\u003cstrong\u003eHardware:\u003c\/strong\u003e Mac Studio M5 Max, 128 GB, 2 TB\u003c\/p\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eDesk-side power for bigger models, still quiet enough for a home office.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Max\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eApple hardware configuration starting from $2,499. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419749937368,"sku":null,"price":2499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_6e8af25b-cfe9-49bd-9626-8e53d9010104.png?v=1790221260"},{"product_id":"puppy-one-256-512","title":"Puppy One 256 \/ 512","description":"\u003cp\u003e\u003cstrong\u003eHardware:\u003c\/strong\u003e Mac Studio M5 Ultra, 512 GB, 4 TB\u003c\/p\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eRun models most people rent from the cloud, entirely on your own machine.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Frontier\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 256-512 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Ultra\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eApple hardware configuration starting from $5,499. Price confirmed at order based on current market band.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419751248088,"sku":null,"price":5499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_d26cc74f-0845-40b2-accd-06a26c614241.png?v=1790221189"},{"product_id":"puppy-one-practice","title":"Puppy One Practice","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\u003cul\u003e\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Unknown\u003c\/li\u003e\u003c\/ul\u003e\u003c\/div\u003e\u003cp\u003eProfessional practice configuration priced at $17,969.69. Verified July 7, 2026. Price confirmed at order based on current market band.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e$17,969.69\u003c\/li\u003e\n\u003cli\u003ePrice verified July 7, 2026\u003c\/li\u003e\n\u003cli\u003eMarket-band pricing confirmed at order\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419751411928,"sku":null,"price":17969.69,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo_ffa02366-d288-43e4-a8ef-2c4b49416785.png?v=1790221135"},{"product_id":"puppy-one-your-own-device","title":"Puppy One · your own device","description":"\u003cp\u003e\u003cstrong\u003eMinimum requirements:\u003c\/strong\u003e macOS on Apple Silicon, Windows, or Linux with LM Studio, and 32 GB+ of memory for the model. Mac is our tested platform; Windows and Linux setups are supported but still being validated.\u003c\/p\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eAlready have a capable machine? We set up Puppy One on it.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Setup service\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 32 GB+\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Any LM Studio-supported\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS \/ Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac tested; others need testing\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eBring your own compatible device and subscribe to Puppy One. Get full access to the Hushh AI platform and Puppy One experience on hardware you already own.\u003c\/p\u003e","brand":"hussh","offers":[{"title":"Default Title","offer_id":52419752493272,"sku":null,"price":69.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/Coming_Soon_white_nologo.png?v=1790221097"},{"product_id":"samsung-galaxy-s26-ultra","title":"Samsung Galaxy S26 Ultra (16 GB, 1 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe broadest set of on-device AI features on Android.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Snapdragon 8 Elite Gen 5\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Android\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e6.9-inch flagship phone featuring the Snapdragon 8 Elite Gen 5 for Galaxy with a Hexagon NPU, up to 16 GB of memory, up to 1 TB of storage, a QHD+ 120 Hz Dynamic AMOLED 2X display, an integrated S Pen, and a 200 MP quad camera system.\u003c\/p\u003e\u003cp\u003eDesigned as an always-on personal endpoint for the One runtime, with Galaxy AI running on device, Samsung Knox for hardware-isolated storage, DeX for desktop mode, and seven years of Android and security updates.\u003c\/p\u003e\u003cp\u003eFits in a pocket with a 5,000 mAh battery and 45 W charging, USB-C 3.2, and the ability to run a 7-billion-parameter model at 4-bit on the 16 GB configuration.\u003c\/p\u003e\u003cp\u003e$949.99 (256 GB, Amazon), down from $1,299.99. 512 GB $1,149.\u003c\/p\u003e","brand":"Samsung","offers":[{"title":"Default Title","offer_id":52419776250072,"sku":"SAM-S26U","price":949.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470659395800.jpg?v=1791848871"},{"product_id":"oneplus-15","title":"OnePlus 15 (16 GB, 512 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA flagship chip and 16 GB for fast on-device AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Snapdragon 8 Elite Gen 5\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Android\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e6.78-inch flagship phone featuring the Snapdragon 8 Elite Gen 5 with a Hexagon NPU, up to 16 GB of memory, up to 512 GB of storage, a 165 Hz AMOLED display, and a 50 MP triple camera system.\u003c\/p\u003e\n\u003cp\u003eDesigned as an always-on personal endpoint for the One runtime, with OxygenOS on Android 16, on-device AI features, and USB-C 3.2 for external storage.\u003c\/p\u003e\n\u003cp\u003eFits in a pocket with a 7,300 mAh silicon-carbon battery and 120 W wired charging, and the ability to run a 7-billion-parameter model at 4-bit in 16 GB of memory.\u003c\/p\u003e","brand":"OnePlus","offers":[{"title":"Default Title","offer_id":52419777298648,"sku":"OP-15","price":749.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470660640984.jpg?v=1791848910"},{"product_id":"samsung-galaxy-tab-s11-ultra","title":"Samsung Galaxy Tab S11 Ultra (16 GB, 1 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA large Android tablet with 16 GB for the app and small models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e MediaTek Dimensity (flagship)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Android\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e14.6-inch tablet featuring the MediaTek Dimensity 9400+ with an NPU 890, up to 16 GB of memory, up to 1 TB of storage, a 120 Hz Dynamic AMOLED 2X display, and an included S Pen.\u003c\/p\u003e\u003cp\u003eDesigned as a large-screen endpoint for the One runtime, with Galaxy AI on device, Samsung DeX for desktop multitasking, Knox for hardware-isolated storage, and seven years of Android and security updates.\u003c\/p\u003e\u003cp\u003eWeighs 692 g at 5.1 mm thin with an 11,600 mAh battery and 45 W charging, USB-C 3.2, and the ability to run a 7-billion-parameter model at 4-bit on the 16 GB configuration.\u003c\/p\u003e\u003cp\u003e$1,199.99 new (256 GB). $799.99 like-new at Woot.\u003c\/p\u003e","brand":"Samsung","offers":[{"title":"Default Title","offer_id":52419780083928,"sku":"SAM-TABS11U","price":1199.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470663033048.jpg?v=1791848910"},{"product_id":"nothing-phone-3","title":"Nothing Phone (3) (16 GB, 512 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003e16 GB at a lower price; good value for the app and small models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e App + future on-device small model\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 16 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Snapdragon 8s Gen 4\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Android\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e App needs iOS 17+ \/ Android 7+; phones don't run Puppy One itself (by design)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e6.67-inch flagship phone featuring the Snapdragon 8s Gen 4 with a Hexagon NPU, up to 16 GB of memory, up to 512 GB of storage, a 120 Hz AMOLED display, a 5,150 mAh battery, and a quad 50 MP camera system including a periscope telephoto.\u003c\/p\u003e\u003cp\u003eDesigned as an always-on personal endpoint for the One runtime, with on-device inference through the Hexagon NPU, Nothing OS on Android 15 with Android 17 scheduled, and the Glyph Matrix on the rear that surfaces status without waking the screen.\u003c\/p\u003e\u003cp\u003eFits in a pocket and runs all day on a single charge, with USB-C and five years of OS updates, and the ability to run a 7-billion-parameter model at 4-bit in 16 GB of memory.\u003c\/p\u003e\u003cp\u003e$599 (256 GB) \/ $699 (512 GB) at Amazon and Best Buy; MSRP $799 \/ $899. Lowest seen: $499 (August 26, 2026, one day).\u003c\/p\u003e","brand":"Nothing","offers":[{"title":"Default Title","offer_id":52419780116696,"sku":"NOT-PHONE3","price":599.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470663065816.jpg?v=1791848911"},{"product_id":"beelink-ser9","title":"Beelink SER9 (Ryzen AI 9 HX 370, 32 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe lowest-cost way in; fits the default model with little to spare.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Entry (tight)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 32 GB shared with the OS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI 9 HX 370 + Radeon 890M\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e 32 GB is shared with Windows, so expect little headroom.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact mini PC featuring the AMD Ryzen AI 9 HX 370 with 12 Zen 5 cores, a 16-compute-unit Radeon 890M GPU, a 50 TOPS XDNA 2 NPU, 32 GB of LPDDR5X-7500 memory, and up to 4 TB across two M.2 slots.\u003c\/p\u003e\n\u003cp\u003eDesigned for small-model inference and agent runtimes on a desk, with Windows 11 Pro preinstalled and Linux supported, Vulkan and ROCm backends for llama.cpp and Ollama, and 2.5 GbE, Wi-Fi 6, and USB4 for expansion.\u003c\/p\u003e\n\u003cp\u003eSits behind a monitor at under 1 kg, draws under 65 W at load from an internal power supply, and runs a 13-billion-parameter model at 4-bit with memory allocated to the GPU.\u003c\/p\u003e\n\u003cp\u003e Memory is soldered.\u003c\/p\u003e","brand":"Beelink","offers":[{"title":"Default Title","offer_id":52419784343768,"sku":"BLK-SER9","price":859.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470666440920.jpg?v=1791848911"},{"product_id":"minisforum-ai-x1-pro","title":"Minisforum AI X1 Pro (Ryzen AI 9 HX 370, 96 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eAn affordable mini PC with enough memory for the default model.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Entry\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 96 GB shared\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI 9 HX 370 + Radeon 890M\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact mini PC featuring the AMD Ryzen AI 9 HX 370 with 12 Zen 5 cores, a 16-compute-unit Radeon 890M GPU, a 50 TOPS XDNA 2 NPU, up to 96 GB of user-upgradable DDR5-5600 SODIMM memory, and up to 12 TB across three M.2 slots.\u003c\/p\u003e\u003cp\u003eDesigned for small-model inference and agent runtimes with room to grow, with Windows 11 Pro preinstalled and Linux supported, Vulkan and ROCm backends for llama.cpp and Ollama, an OCuLink port for an external GPU, and dual 2.5 GbE and USB4.\u003c\/p\u003e\u003cp\u003eSits behind a monitor at roughly 1 kg, draws under 70 W at load, includes a fingerprint reader, and runs a 32-billion-parameter model at 4-bit with 96 GB of memory.\u003c\/p\u003e\u003cp\u003e$1,359 (32 GB, 1 TB). Memory and storage are user-upgradable.\u003c\/p\u003e","brand":"Minisforum","offers":[{"title":"Default Title","offer_id":52419785982168,"sku":"MSF-AIX1PRO","price":1359.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470668144856.jpg?v=1791848911"},{"product_id":"gmktec-evo-x2-128gb","title":"GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA compact 128 GB mini PC for always-on Puppy One at a lower price.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ 395 (Strix Halo)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact desktop AI system featuring the AMD Ryzen AI Max+ 395 with 16 Zen 5 cores, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5X-8000 unified memory at 256 GB\/s, and up to 8 TB across two M.2 slots.\u003c\/p\u003e\n\u003cp\u003eDesigned to run and fine-tune large open-weight models locally with up to 96 GB of memory allocatable to the GPU on Windows and 110 GB on Linux, with Windows 11 Pro preinstalled, ROCm and Vulkan for llama.cpp, Ollama, and LM Studio, and 2.5 GbE, Wi-Fi 7, and USB4 for expansion.\u003c\/p\u003e\n\u003cp\u003eSits on a desk at roughly 2 kg, draws under 140 W at peak from an internal power supply, and runs a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e\n\u003cp\u003e$3,499.99 (128 GB, 1 TB); $3,649.99 with 2 TB. The 64 GB model is $1,999.99. Confirm price at order.\u003c\/p\u003e","brand":"GMKtec","offers":[{"title":"Default Title","offer_id":52419787882712,"sku":"GMK-EVOX2-128","price":3499.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470669848792.jpg?v=1791848911"},{"product_id":"asus-nuc-15-pro","title":"ASUS NUC 15 Pro (Core Ultra 7, 96 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA budget always-on box; 96 GB fits the default model, but it answers slower than GPU machines.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Entry (slower)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 96 GB system RAM (integrated GPU)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Intel Core Ultra 7 + Arc iGPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e No discrete GPU.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact mini PC featuring the Intel Core Ultra 7 255H with 16 cores, an Intel Arc 140T GPU, a 13 TOPS NPU, up to 96 GB of user-upgradable DDR5-6400 SODIMM memory, and up to 8 TB across two M.2 slots.\u003c\/p\u003e\u003cp\u003eDesigned for small-model inference, agent runtimes, and enterprise desktop duty, with Windows 11 Pro or Linux, Intel OpenVINO across CPU, GPU, and NPU, Thunderbolt 4, 2.5 GbE, Wi-Fi 7, and Intel vPro for fleet management.\u003c\/p\u003e\u003cp\u003eSits behind a monitor at under 1 kg with a VESA mount, draws under 65 W at load, and runs a 13-billion-parameter model at 4-bit on the CPU and Arc GPU with 96 GB of memory.\u003c\/p\u003e\u003cp\u003eFrom ~$800 barebone; add memory and storage. Configured 32 GB \/ 1 TB roughly $1,100.\u003c\/p\u003e","brand":"ASUS","offers":[{"title":"Default Title","offer_id":52419799843032,"sku":"ASUS-NUC15PRO","price":800.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470672699608.jpg?v=1791848911"},{"product_id":"hp-z2-mini-g1a-128gb","title":"HP Z2 Mini G1a (Ryzen AI Max+ PRO 395, 128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA business-grade 128 GB mini workstation with HP support.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ PRO 395\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact 2.5-liter desktop workstation featuring the AMD Ryzen AI Max+ PRO 395 with 16 Zen 5 cores, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5X-8000 unified memory at 256 GB\/s, and up to 8 TB across two M.2 slots.\u003c\/p\u003e\n\u003cp\u003eDesigned to run and fine-tune large open-weight models on an ISV-certified enterprise desktop, with Windows 11 Pro or Ubuntu, ROCm and Vulkan for llama.cpp, Ollama, and LM Studio, up to 96 GB allocatable to the GPU, HP Wolf Security, and 2.5 GbE with optional 10 GbE.\u003c\/p\u003e\n\u003cp\u003eSits behind a monitor or in a rack sled at roughly 1.8 kg, draws under 140 W at peak, and runs a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e\n\u003cp\u003eHP configurator pricing; confirm at order.\u003c\/p\u003e","brand":"HP","offers":[{"title":"Default Title","offer_id":52419812065496,"sku":"HP-Z2MINI-G1A-128","price":3500.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470675386584.jpg?v=1791848912"},{"product_id":"macbook-pro-16-m5-max-128gb-1","title":"Apple MacBook Pro 16 M5 Max (128 GB, 8 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eThe most capable laptop for running your own AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Max\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e16-inch laptop featuring the Apple M5 Max chip with an 18-core CPU, a 40-core GPU with Neural Accelerators, and a 16-core Neural Engine, 128 GB of unified memory, up to 8 TB of SSD storage, a Liquid Retina XDR display at 120 Hz, and Thunderbolt 5 at 120 Gb\/s.\u003c\/p\u003e\n\u003cp\u003eDesigned to run and fine-tune frontier-class open-weight models on a laptop, with macOS, Core ML, and Apple's MLX framework, Xcode for developers, and the same silicon lineage as Mac Studio so models move between them unchanged.\u003c\/p\u003e\n\u003cp\u003eCarries at 2.1 kg with up to 24 hours of battery for inference sessions unplugged, a 140 W adapter, Secure Enclave and Touch ID, and the ability to run a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419857907928,"sku":"APL-MBP16-M5MAX-128","price":9999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470683676888.jpg?v=1791848912"},{"product_id":"macbook-pro-14-m5-pro-1","title":"Apple MacBook Pro 14 M5 Pro (64 GB, 4 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA portable Puppy One with room for the default model and longer chats.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 64 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Apple M5 Pro\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e macOS\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Mac: same platform as the tested setup (M4 Max)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e14-inch laptop featuring the Apple M5 Pro chip with up to a 14-core CPU, a 20-core GPU with Neural Accelerators, and a 16-core Neural Engine, 24 GB to 64 GB of unified memory, up to 4 TB of SSD storage, a Liquid Retina XDR display at 120 Hz, and Thunderbolt 5.\u003c\/p\u003e\n\u003cp\u003eDesigned for local inference and development on the go, with macOS, Core ML, and Apple's MLX framework, Xcode for developers, and three Thunderbolt 5 ports for external storage and displays.\u003c\/p\u003e\n\u003cp\u003eCarries at 1.6 kg with up to 24 hours of battery, a 96 W adapter, Secure Enclave and Touch ID, and the ability to run a 32-billion-parameter model at 8-bit or a 70-billion-parameter model at 4-bit on the 64 GB configuration.\u003c\/p\u003e","brand":"Apple","offers":[{"title":"Default Title","offer_id":52419865247960,"sku":"APL-MBP14-M5PRO","price":2499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470685446360.jpg?v=1791848912"},{"product_id":"lenovo-legion-pro-7i-gen-10-rtx-5090","title":"Lenovo Legion Pro 7i Gen 10 (RTX 5090 24 GB, 64 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA gaming-class laptop that runs the model entirely on its 24 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX 5090 (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e16-inch portable AI workstation featuring an Intel Core Ultra 9 275HX processor, an NVIDIA GeForce RTX 5090 Laptop GPU with 24 GB of GDDR7 at up to 175 W, up to 64 GB of DDR5-6400 memory across two user-upgradable SODIMM slots, dual PCIe Gen4 M.2 slots for up to 4 TB, and a 2.5K 240 Hz OLED display.\u003c\/p\u003e\n\u003cp\u003eDesigned for local inference, fine-tuning, and agent development on the fastest GPU available in a laptop, with Windows 11 and full CUDA, PyTorch, and Ollama support, Thunderbolt 4 for external storage and displays, and Lenovo's Legion Coldfront vapor-chamber cooling to hold sustained GPU clocks under load.\u003c\/p\u003e\n\u003cp\u003eCarries in a backpack at roughly 2.7 kg with a 99.99 Wh battery for short sessions unplugged and a 400 W adapter for full performance, and runs a 32-billion-parameter model at 4-bit or a 13-billion-parameter model at 8-bit entirely in GPU memory.\u003c\/p\u003e","brand":"Lenovo","offers":[{"title":"Default Title","offer_id":52419870589144,"sku":"LEN-LEGIONPRO7I-G10-5090","price":2999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470687183064.jpg?v=1791848912"},{"product_id":"asus-rog-flow-z13-128gb","title":"ASUS ROG Flow Z13 (Ryzen AI Max+ 395, 128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003e128 GB in a 2-in-1 tablet laptop.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ 395\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e13.4-inch detachable 2-in-1 featuring the AMD Ryzen AI Max+ 395 with 16 Zen 5 cores, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5X-8000 unified memory at 256 GB\/s, up to 2 TB of PCIe Gen4 storage, and a 2.5K 180 Hz Nebula display.\u003c\/p\u003e\u003cp\u003eDesigned to run large open-weight models on the smallest machine that holds 128 GB, with Windows 11, ROCm and Vulkan for llama.cpp, Ollama, and LM Studio, up to 96 GB allocatable to the GPU, and USB4 plus the ROG XG Mobile port for an external GPU.\u003c\/p\u003e\u003cp\u003eCarries as a tablet at 1.2 kg with a 70 Wh battery and a 200 W adapter, includes a detachable keyboard cover and kickstand, and runs a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e\u003cp\u003e$2,699 (128 GB) at launch; the 32 GB model has sold for $2,069.99. Verify the 128 GB street price before order.\u003c\/p\u003e","brand":"ASUS","offers":[{"title":"Default Title","offer_id":52419885531352,"sku":"ASUS-FLOWZ13-128","price":2699.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470689476824.jpg?v=1791848912"},{"product_id":"hp-zbook-ultra-g1a-128gb","title":"HP ZBook Ultra G1a (Ryzen AI Max+ PRO 395, 128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA thin business laptop with 128 GB for local AI.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ PRO 395\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e14-inch mobile workstation featuring the AMD Ryzen AI Max+ PRO 395 with 16 Zen 5 cores, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5X-8000 unified memory at 256 GB\/s, up to 4 TB of PCIe Gen4 storage, and a 2.8K OLED display.\u003c\/p\u003e\n\u003cp\u003eDesigned to run and fine-tune large open-weight models on an ISV-certified laptop, with Windows 11 Pro or Ubuntu, ROCm and Vulkan for llama.cpp, Ollama, and LM Studio, up to 96 GB allocatable to the GPU, HP Wolf Security, and USB4 at 40 Gb\/s.\u003c\/p\u003e\n\u003cp\u003eCarries at 1.6 kg with a 74.5 Wh battery and a 140 W adapter, includes a fingerprint reader and IR camera, and runs a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e","brand":"HP","offers":[{"title":"Default Title","offer_id":52419894837464,"sku":"HP-ZBOOKULTRA-G1A-128","price":3967.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470691901656.jpg?v=1791848912"},{"product_id":"razer-blade-16-rtx-5090","title":"Razer Blade 16 (RTX 5090 24 GB, 64 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA premium thin laptop with a 24 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX 5090 (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e16-inch thin-and-light AI laptop featuring the AMD Ryzen AI 9 HX 370, an NVIDIA GeForce RTX 5090 Laptop GPU with 24 GB of GDDR7 at up to 160 W, up to 64 GB of DDR5-5600 memory, up to 4 TB across two M.2 slots, and a QHD+ 240 Hz OLED display.\u003c\/p\u003e\n\u003cp\u003eDesigned for local inference and fine-tuning on the fastest laptop GPU in a 15 mm chassis, with Windows 11 and full CUDA, PyTorch, and Ollama support, Thunderbolt 5 for external storage and displays, and a vapor chamber with Razer's thermal hood.\u003c\/p\u003e\n\u003cp\u003eCarries at 2.1 kg with a 90 Wh battery and a 280 W GaN adapter, machined from a single block of aluminum, and runs a 32-billion-parameter model at 4-bit or a 13-billion-parameter model at 8-bit entirely in GPU memory.\u003c\/p\u003e","brand":"Razer","offers":[{"title":"Default Title","offer_id":52419899130072,"sku":"RZR-BLADE16-5090","price":4499.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470692524248.jpg?v=1791848912"},{"product_id":"msi-titan-18-hx","title":"MSI Titan 18 HX (RTX 5090 24 GB, 96 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eAn 18-inch powerhouse with a 24 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX 5090 (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e18-inch desktop-replacement laptop featuring an Intel Core Ultra 9 285HX processor, an NVIDIA GeForce RTX 5090 Laptop GPU with 24 GB of GDDR7 at up to 175 W, up to 96 GB of DDR5-6400 memory, up to 6 TB across three M.2 slots including PCIe Gen5, and an 18-inch 4K mini-LED 120 Hz display.\u003c\/p\u003e\u003cp\u003eDesigned for local inference, fine-tuning, and content creation on the fastest laptop GPU with the most system memory in its class, with Windows 11, full CUDA, PyTorch, and Ollama support, Thunderbolt 5, and a Cherry mechanical keyboard.\u003c\/p\u003e\u003cp\u003eCarries at roughly 3.6 kg with a 99.9 Wh battery and a 400 W adapter, and runs a 32-billion-parameter model at 4-bit in GPU memory or a 70-billion-parameter model at 4-bit by spilling into 96 GB of system RAM.\u003c\/p\u003e\u003cp\u003e~$5,500. MSI configurator and retail; confirm at order.\u003c\/p\u003e","brand":"MSI","offers":[{"title":"Default Title","offer_id":52419902308568,"sku":"MSI-TITAN18HX","price":5499.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470692950232.jpg?v=1791848913"},{"product_id":"framework-laptop-16","title":"Framework Laptop 16 (RTX 5070 8 GB, 96 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA repairable everyday laptop; runs the app well, Puppy One only in a pinch.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Runs, slowly\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 8 GB GPU (the model spills into RAM)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX 5070 (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e An 8 GB GPU is too small for the default model.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e16-inch modular laptop featuring the AMD Ryzen AI 9 HX 370 with 12 Zen 5 cores and a 50 TOPS XDNA 2 NPU, an optional NVIDIA GeForce RTX 5070 Laptop graphics module with 8 GB of GDDR7, up to 96 GB of user-upgradable DDR5-5600 SODIMM memory, and up to 8 TB across two M.2 slots.\u003c\/p\u003e\u003cp\u003eDesigned for developers who want a repairable, upgradable machine, with Windows 11 or Linux, CUDA on the graphics module and ROCm on the integrated Radeon 890M, swappable expansion cards for ports, and a graphics module bay that can be upgraded as new modules ship.\u003c\/p\u003e\u003cp\u003eCarries at 2.1 kg with the graphics module and an 85 Wh battery, every part user-replaceable with a single screwdriver, and runs a 13-billion-parameter model at 4-bit on the graphics module or a 32-billion-parameter model at 4-bit in system memory.\u003c\/p\u003e\u003cp\u003e~$3,000 configured with the RTX 5070 module; ~$2,000 without. Framework configurator.\u003c\/p\u003e","brand":"Framework","offers":[{"title":"Default Title","offer_id":52419907420376,"sku":"FW-LAPTOP16-AI300","price":2999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470694916312.jpg?v=1791848913"},{"product_id":"acer-veriton-gn100","title":"Acer Veriton GN100 (128 GB, 4 TB)","description":"\u003cdiv class=\"hushh-quote-enquiry\" data-version=\"1\"\u003e\u003cp\u003e\u003cstrong\u003ePricing and availability on request.\u003c\/strong\u003e \u003ca href=\"mailto:support@hushh.ai?subject=Quote%20request%3A%20Acer%20Veriton%20GN100%20(128%20GB%2C%204%20TB)\"\u003eEmail support@hushh.ai to request a quote\u003c\/a\u003e. Please include the product name and delivery ZIP code. We will confirm the configuration, final price, and availability before accepting an order.\u003c\/p\u003e\u003c\/div\u003e\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-10-12\"\u003e\n\u003cp\u003e\u003cstrong\u003eA palm-sized Grace Blackwell box with room for your agent and much bigger models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA GB10 Grace Blackwell\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e DGX OS (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux ARM64 (LM Studio officially supports GB10)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Not sold on Acer's US store\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eUltra-compact personal AI workstation featuring the NVIDIA GB10 Grace Blackwell Superchip, equipped with 128 GB of unified LPDDR5X memory, a 20-core Arm CPU, 4 TB of NVMe storage, and delivering up to 1 PFLOPS of FP4 AI performance in a 150 mm square chassis.\u003c\/p\u003e\u003cp\u003eDesigned to work locally with large AI models, and scale to larger workloads by connecting two Acer Veriton GN100 systems with the NVIDIA ConnectX-7 SmartNIC, pre-installed with the latest NVIDIA AI software stack and support for common developer tools and frameworks, including PyTorch, Jupyter, and Ollama.\u003c\/p\u003e\u003cp\u003eSpace-efficient and secure, with Kensington lock support, Wi-Fi 7 and 10 GbE, a standard outlet at under 240 W, and the ability to link two units for handling AI models up to 405 billion parameters.\u003c\/p\u003e\u003cp\u003eAcer doesn't sell the GN100 on its own US store. Request information and we'll confirm price and delivery.\u003c\/p\u003e","brand":"Acer","offers":[{"title":"Request information","offer_id":52419929735384,"sku":"ACER-GN100","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470699110616.jpg?v=1791848913"},{"product_id":"asus-ascent-gx10","title":"ASUS Ascent GX10 (128 GB, 4 TB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-10-12\"\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA's desktop agent computer in an ASUS build, made to run agents 24\/7.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e NVIDIA GB10 Grace Blackwell\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e DGX OS (Ubuntu, ARM64)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux ARM64 (LM Studio officially supports GB10)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Limited (out of stock on the ASUS eShop)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eUltra-compact personal AI workstation featuring the NVIDIA GB10 Grace Blackwell Superchip, equipped with 128 GB of unified LPDDR5X memory, a 20-core Arm CPU, 1 TB, 2 TB, or 4 TB of NVMe storage, and delivering up to 1 PFLOPS of FP4 AI performance in a 150 mm square chassis.\u003c\/p\u003e\u003cp\u003eDesigned to prototype, fine-tune, and run large models locally, and scale to larger workloads by linking two Ascent GX10 systems over the built-in NVIDIA ConnectX-7 SmartNIC at 200 Gb\/s, pre-installed with the NVIDIA AI software stack, CUDA, and support for PyTorch, Jupyter, and Ollama.\u003c\/p\u003e\u003cp\u003eSpace-efficient enough to sit under a monitor at 150 × 150 × 51 mm and 1.48 kg, powered from a standard outlet at under 240 W, with Wi-Fi 7, 10 GbE, four USB-C ports with DisplayPort 2.1, HDMI 2.1, and a Kensington lock, and the ability to link two units for models up to 405 billion parameters.\u003c\/p\u003e\u003cp\u003eASUS US eShop prices: $5,999 (1 TB), $6,999 (2 TB), $7,999 (4 TB Gen5).\u003c\/p\u003e","brand":"ASUS","offers":[{"title":"1 TB Gen4","offer_id":52457681518808,"sku":"ASUS-GX10-1TB","price":5999.0,"currency_code":"USD","in_stock":true},{"title":"2 TB Gen4","offer_id":52457681551576,"sku":"ASUS-GX10-2TB","price":6999.0,"currency_code":"USD","in_stock":true},{"title":"4 TB Gen5","offer_id":52457681584344,"sku":"ASUS-GX10-4TB","price":7999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470699798744.jpg?v=1791848913"},{"product_id":"amd-ryzen-ai-halo-dev-box","title":"AMD Ryzen AI Halo Developer Platform (128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eAMD's own 128 GB local-AI box: a quiet, always-on home for Puppy One.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ 395 (Strix Halo)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux \/ Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact desktop AI development system featuring the AMD Ryzen AI Max+ 395 with 16 Zen 5 cores at up to 5.1 GHz, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5x-8000 unified memory at 256 GB\/s, a removable 2 TB NVMe SSD, and delivering up to 126 TOPS of INT8 AI performance.\u003c\/p\u003e\u003cp\u003eDesigned to run and fine-tune large open-weight models locally on a standard x86 platform, with Windows 11 Pro or Linux preloaded, ROCm and Vulkan backends for llama.cpp, Ollama, and LM Studio, AMD's AI Playbooks for step-by-step inference and fine-tuning workflows, and 10 GbE and Wi-Fi 7 for clustering multiple units or serving on a local network.\u003c\/p\u003e\u003cp\u003eSpace-efficient enough to sit beside a monitor, powered from a 120 W external supply, with three USB-C ports including DisplayPort, HDMI 2.1b, and Bluetooth 5.4, and the ability to run models up to 200 billion parameters in unified memory, including a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit with room for context.\u003c\/p\u003e\u003cp\u003e$3,999.99. Micro Center, in-store pickup. Windows 11 Pro or Linux; identical hardware.\u003c\/p\u003e","brand":"AMD","offers":[{"title":"Windows 11 Pro","offer_id":52457681387736,"sku":"AMD-HALO-DEV-WIN","price":3999.99,"currency_code":"USD","in_stock":true},{"title":"Linux","offer_id":52457681420504,"sku":"AMD-HALO-DEV-LNX","price":3999.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470700749016.jpg?v=1791848913"},{"product_id":"framework-desktop-128gb","title":"Framework Desktop (Ryzen AI Max+ 395, 128 GB)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA repairable, quiet 128 GB desktop that runs your agent around the clock.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 128 GB unified\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e Ryzen AI Max+ 395 (Strix Halo)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows \/ Linux\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Linux \/ Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eCompact 4.5-liter desktop AI system featuring the AMD Ryzen AI Max+ 395 with 16 Zen 5 cores, a 40-compute-unit Radeon 8060S GPU, a 50 TOPS XDNA 2 NPU, 128 GB of LPDDR5x-8000 unified memory at 256 GB\/s, and two PCIe Gen4 M.2 slots for up to 16 TB of storage.\u003c\/p\u003e\u003cp\u003eDesigned to run and fine-tune large open-weight models locally with up to 96 GB of memory allocatable to the GPU on Windows and 110 GB on Linux, with Fedora, Ubuntu, or Windows 11 support, ROCm and Vulkan for llama.cpp, Ollama, and LM Studio, and a PCIe x4 slot and 5 GbE for clustering multiple units.\u003c\/p\u003e\u003cp\u003eSits on a desk with a standard 400 W internal power supply and a swappable front panel, draws under 140 W at peak, and runs a 70-billion-parameter model at 8-bit or a 120-billion-parameter model at 4-bit entirely in unified memory.\u003c\/p\u003e\u003cp\u003e$3,449. Framework; memory is soldered. Currently out of stock.\u003c\/p\u003e","brand":"Framework","offers":[{"title":"Default Title","offer_id":52419945038040,"sku":"FW-DESKTOP-395-128GB","price":3449.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470702649560.jpg?v=1791848913"},{"product_id":"dell-pro-max-18-plus","title":"Dell Pro Max 18 Plus (RTX PRO 5000 24 GB, 128 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eAn 18-inch mobile workstation with a 24 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 24 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX PRO 5000 Blackwell (laptop)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNote:\u003c\/strong\u003e Laptop: answers only while awake and on power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003e18-inch desktop-replacement mobile workstation featuring an Intel Core Ultra 9 285HX processor with vPro, an NVIDIA RTX PRO 5000 Blackwell GPU with 24 GB of GDDR7 at 175 W on a replaceable module, up to 128 GB of DDR5-6400 CAMM2 memory (256 GB per spec), up to 16 TB across four PCIe Gen5 SSDs with RAID, and an 18-inch QHD+ 120 Hz display.\u003c\/p\u003e\u003cp\u003eDesigned for local inference, fine-tuning, and rendering on a certified professional GPU, with Windows 11 Pro, NVIDIA AI Enterprise and CUDA support, Intel OpenVINO across the iGPU and NPU, Thunderbolt 5 for external storage and displays, and Dell's DGFF graphics module that allows the GPU to be serviced or upgraded.\u003c\/p\u003e\u003cp\u003eCarries at roughly 3.5 kg with a bottom hatch for user-serviceable memory and storage, optional 5G WWAN, ISV certifications and enterprise manageability, and the ability to run a 32-billion-parameter model at 4-bit in GPU memory, or far larger models by spilling into system RAM.\u003c\/p\u003e\u003cp\u003e$11,674 as configured (Core Ultra 9 285HX, RTX PRO 5000, 64 GB CAMM2, 2 TB). From $8,284 with the RTX PRO 5000.\u003c\/p\u003e","brand":"Dell","offers":[{"title":"Default Title","offer_id":52419949494488,"sku":"DELL-MB18250-RTXPRO5000","price":11674.21,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470703435992.jpg?v=1791848914"},{"product_id":"rtx-5090-tower-puget-diy","title":"Puget Systems RTX 5090 Tower (32 GB, 192 GB RAM)","description":"\u003cdiv class=\"puppy-one-fit\" data-catalog=\"2026-09-27\"\u003e\n\u003cp\u003e\u003cstrong\u003eA hand-built, quiet tower; fast local AI on a 32 GB GPU.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003ePuppy One fit:\u003c\/strong\u003e Recommended\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eMemory for models:\u003c\/strong\u003e 32 GB GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eChip \/ GPU:\u003c\/strong\u003e RTX 5090\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eOS:\u003c\/strong\u003e Windows\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidation:\u003c\/strong\u003e Needs testing: Windows x64\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAvailability:\u003c\/strong\u003e Available\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\u003cp\u003eFull-size desktop workstation built around a single NVIDIA GeForce RTX 5090 with 32 GB of GDDR7 at 1.79 TB\/s delivering up to 3,352 AI TOPS at FP4, paired with an Intel Core Ultra 9 285K or AMD Ryzen 9 9950X, up to 192 GB of DDR5 memory, PCIe Gen5 NVMe storage, and a 1,000 W or larger power supply.\u003c\/p\u003e\u003cp\u003eDesigned for local inference, fine-tuning, and image or video generation on the fastest single consumer GPU, with Windows 11 or Ubuntu and full CUDA, PyTorch, ComfyUI, and Ollama support, built and burned in by Puget Systems with lifetime labor support.\u003c\/p\u003e\u003cp\u003eFloor-standing on a dedicated 15 A circuit at roughly 800 W under sustained load, no ECC memory or ISV certification, and the ability to run a 32-billion-parameter model at 8-bit or 70 billion at 4-bit entirely in GPU memory.\u003c\/p\u003e\u003cp\u003eFrom $5,207. Puget Systems configurator; typical build $6,000–7,000. Card supply is the constraint.\u003c\/p\u003e","brand":"Puget Systems","offers":[{"title":"Default Title","offer_id":52419966402776,"sku":"PUGET-RTX5090-TOWER","price":5207.44,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/9470707237080.jpg?v=1791848914"}],"url":"https:\/\/shop.hushh.ai\/collections\/all.oembed?page=2","provider":"Hussh Shop","version":"1.0","type":"link"}