{"title":"Mini PCs","description":"\u003cp\u003eCompact AI powerhouses for your desktop, Agent One-ready.\u003c\/p\u003e","products":[{"product_id":"mac-mini-m4","title":"Apple Mac mini M4 (32 GB, 2 TB)","description":"\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\u003cp\u003e$799 (16 GB, 256 GB) after Apple's June 25 repricing. Lowest seen: $469 (June 2025, pre-hike).\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/support.apple.com\/en-us\/121555\" target=\"_blank\" rel=\"noopener\"\u003eApple\u003c\/a\u003e.\u003c\/em\u003e\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\/mac-mini__dvce2jrm11w2_og_8c15e218-521e-44a2-8efc-de3744f48588.jpg?v=1789409965"},{"product_id":"mac-mini-m4-pro","title":"Apple Mac mini M4 Pro (64 GB, 8 TB)","description":"\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\u003cp\u003e$1,599 (24 GB, 512 GB) after Apple's June 25 repricing. Lowest seen: $1,173 (pre-hike).\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/support.apple.com\/en-us\/121555\" target=\"_blank\" rel=\"noopener\"\u003eApple\u003c\/a\u003e.\u003c\/em\u003e\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\/mac-mini__dvce2jrm11w2_og.jpg?v=1789409965"},{"product_id":"nvidia-dgx-spark","title":"NVIDIA DGX Spark (128 GB, 4 TB)","description":"\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$4,699 Founders Edition, direct from NVIDIA. Up $700 from launch in February 2026; unchanged since June.\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.nvidia.com\/en-us\/products\/workstations\/dgx-spark\/\" target=\"_blank\" rel=\"noopener\"\u003eNVIDIA\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":52419725164760,"sku":"NV-DGX-SPARK","price":4699.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/NVIDIA_DGX_Spark_white.png?v=1790222640"},{"product_id":"dual-dgx-spark-linked","title":"NVIDIA Dual DGX Spark, linked (256 GB, 8 TB)","description":"\u003cp\u003eTwo NVIDIA DGX Spark systems linked over their built-in ConnectX-7 SmartNICs at 200 Gb\/s, pooling 256 GB of unified LPDDR5X memory, 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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.nvidia.com\/en-us\/products\/workstations\/dgx-spark\/\" target=\"_blank\" rel=\"noopener\"\u003eNVIDIA\u003c\/a\u003e.\u003c\/em\u003e\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\/NVIDIA_DGX_Spark_white_96bd703b-b228-448e-ad77-f22c2a0cd314.png?v=1790222745"},{"product_id":"beelink-ser9","title":"Beelink SER9 Pro (Ryzen AI 9 HX 370, 32 GB)","description":"\u003cp\u003eCompact mini PC (sold by Beelink as the SER9 Pro) 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 8 TB across two PCIe 4.0 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\u003eMemory is soldered. $1,149 at Beelink (list $1,399), September 2026.\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.bee-link.com\/products\/beelink-ser9-ai-9-hx-370\" target=\"_blank\" rel=\"noopener\"\u003eBeelink\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"Beelink","offers":[{"title":"Default Title","offer_id":52419784343768,"sku":"BLK-SER9","price":1149.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/6924118a195c99bfa661db132f5d41c3.webp?v=1790219097"},{"product_id":"minisforum-ai-x1-pro","title":"Minisforum AI X1 Pro (Ryzen AI 9 HX 370, 96 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.minisforum.com\/products\/minisforum-ai-x1-pro\" target=\"_blank\" rel=\"noopener\"\u003eMinisforum\u003c\/a\u003e.\u003c\/em\u003e\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\/Compressed_AI_X1_Pro-370.png?v=1789409966"},{"product_id":"gmktec-evo-x2-128gb","title":"GMKtec EVO-X2 (Ryzen AI Max+ 395, 128 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.gmktec.com\/products\/amd-ryzen%E2%84%A2-ai-max-395-evo-x2-ai-mini-pc\" target=\"_blank\" rel=\"noopener\"\u003eGMKtec\u003c\/a\u003e.\u003c\/em\u003e\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\/GMKtec-EVO-X2-003_ad_l.jpg?v=1790218988"},{"product_id":"asus-nuc-15-pro","title":"ASUS NUC 15 Pro (Core Ultra 7, 96 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.asus.com\/us\/displays-desktops\/nucs\/nuc-mini-pcs\/asus-nuc-15-pro\/\" target=\"_blank\" rel=\"noopener\"\u003eASUS\u003c\/a\u003e.\u003c\/em\u003e\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\/unnamed.png?v=1789409967"},{"product_id":"hp-z2-mini-g1a-128gb","title":"HP Z2 Mini G1a (Ryzen AI Max+ PRO 395, 128 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.hp.com\/us-en\/workstations\/z2-mini-a.html\" target=\"_blank\" rel=\"noopener\"\u003eHP\u003c\/a\u003e.\u003c\/em\u003e\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\/move_full.jpg?v=1790218911"},{"product_id":"acer-veriton-gn100","title":"Acer Veriton GN100 (128 GB, 4 TB)","description":"\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\u003e$3,999.99 (DT.R6LAA.001). Staples, Best Buy, Connection — backordered at all three. The cheapest 4 TB GB10 box in the US on paper.\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.acer.com\/us-en\/desktops-and-all-in-ones\/veriton-workstations\/veriton-gn100-ai-mini-workstation\" target=\"_blank\" rel=\"noopener\"\u003eAcer\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"Acer","offers":[{"title":"Default Title","offer_id":52419929735384,"sku":"ACER-GN100","price":3999.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/c9d3b019-483e-474c-8bdf-15242ee46065.jpg?v=1789759505"},{"product_id":"asus-ascent-gx10","title":"ASUS Ascent GX10 (128 GB, 4 TB)","description":"\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\u003e$3,999 (1 TB), $4,599 (2 TB), $5,999 (4 TB) at Amazon. Lowest seen: $3,461 (1 TB, March 2026).\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.asus.com\/us\/networking-iot-servers\/desktop-ai-supercomputer\/ultra-small-ai-supercomputers\/asus-ascent-gx10\/\" target=\"_blank\" rel=\"noopener\"\u003eASUS\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"ASUS","offers":[{"title":"1 TB Gen4","offer_id":52457681518808,"sku":"ASUS-GX10-1TB","price":3999.0,"currency_code":"USD","in_stock":true},{"title":"2 TB Gen4","offer_id":52457681551576,"sku":"ASUS-GX10-2TB","price":4599.0,"currency_code":"USD","in_stock":true},{"title":"4 TB Gen5","offer_id":52457681584344,"sku":"ASUS-GX10-4TB","price":5999.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/unnamed_d14557a9-97a4-4d38-a2f0-a938416c489f.png?v=1789409994"},{"product_id":"amd-ryzen-ai-halo-dev-box","title":"AMD Ryzen AI Halo Developer Platform (128 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.amd.com\/en\/products\/processors\/desktops\/ryzen\/ryzen-ai-halo\/ryzen-ai-max-plus-395.html\" target=\"_blank\" rel=\"noopener\"\u003eAMD\u003c\/a\u003e.\u003c\/em\u003e\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\/711961_049643_01_front_comping.jpg?v=1789759398"},{"product_id":"framework-desktop-128gb","title":"Framework Desktop (Ryzen AI Max+ 395, 128 GB)","description":"\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\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/frame.work\/desktop\" target=\"_blank\" rel=\"noopener\"\u003eFramework\u003c\/a\u003e.\u003c\/em\u003e\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\/3bay32p8nnpegez5s3tdzor1dhwo_b0923abc-4da9-4f90-901b-d18278104b60.jpg?v=1789409993"},{"product_id":"dell-pro-max-with-gb10","title":"Dell Pro Max GB10 (128 GB, 4 TB)","description":"\u003cp\u003eUltra-compact personal AI workstation featuring the NVIDIA GB10 Grace Blackwell Superchip, equipped with 128 GB of unified LPDDR5X memory, up to 4 TB of NVMe storage, a 20-core Arm CPU, 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 Dell Pro Max with GB10 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, with Dell Pro Max management and Dell ProSupport behind it.\u003c\/p\u003e\u003cp\u003eSpace-efficient enough to sit under a monitor, powered from a standard outlet at under 240 W, with Wi-Fi 7 and 10 GbE, and the ability to link two units for models up to 405 billion parameters.\u003c\/p\u003e\u003cp\u003e$4,757. Ships from Dell.\u003c\/p\u003e\u003cp\u003e\u003cem\u003eSpecs \u0026amp; details via \u003ca href=\"https:\/\/www.dell.com\/en-us\/shop\/desktop-computers\/dell-pro-max-with-gb10\/spd\/dell-pro-max-fcm1253-micro\" target=\"_blank\" rel=\"noopener\"\u003eDell\u003c\/a\u003e.\u003c\/em\u003e\u003c\/p\u003e","brand":"Dell","offers":[{"title":"Default Title","offer_id":52419979837656,"sku":"DELL-PROMAX-GB10-4TB","price":4757.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0839\/7039\/2280\/files\/nvidia-blackwell-products-gb10-update.avif?v=1789174561"}],"url":"https:\/\/shop.hushh.ai\/collections\/mini-pcs.oembed","provider":"Hussh Shop","version":"1.0","type":"link"}