AI machines for local LLMs

A buying reference for prebuilt machines that run large open-weight models locally - unified-memory appliances and large-VRAM desktops - with starting prices and where to buy.

In short: To run 70B-class models locally without building a multi-GPU rig, a unified-memory machine is the simplest path. The NVIDIA DGX Spark (128 GB) and AMD Strix Halo mini-PCs (128 GB, ~96 GB usable) handle 70B at Q4; an Apple Mac Studio (96 GB unified) is the quietest option; and the NVIDIA DGX Station (GB300, 748 GB) targets trillion-parameter work. The table below has current starting prices and vendors - figures are indicative, so verify before buying.

MachineMemoryBandwidthModels it runsStarting priceWhere to buy
NVIDIA DGX Spark128 GB273 GB/sfalcon:180b, deepseek-v4-flash, zephyr:141b +385 morefrom $4,699NVIDIA Marketplace, Micro Center, Amazon
NVIDIA DGX Station (GB300)748 GB7100 GB/skimi-k2.5, kimi-k2.6, kimi-k2.7-code +411 moreContact for pricingNVIDIA DGX Station, MSI XpertStation, Exxact, Amazon
Apple Mac Studio (M3 Ultra)96 GB819 GB/scommand-r-plus:104b, llama3.2-vision:90b, qwen3-next:80b +371 morefrom $3,999Apple Store, Amazon
Framework Desktop (Ryzen AI Max+ 395)128 GB256 GB/szephyr:141b, dbrx:132b, mistral-medium-3.5:128b +383 morefrom $2,459Framework, Amazon
GMKtec EVO-X2 (Ryzen AI Max+ 395)128 GB256 GB/szephyr:141b, dbrx:132b, mistral-medium-3.5:128b +383 morefrom $1,999GMKtec, Micro Center, Amazon
HP Z2 Mini G1a (Ryzen AI Max+ PRO 395)128 GB256 GB/szephyr:141b, dbrx:132b, mistral-medium-3.5:128b +383 morefrom $3,343HP, Micro Center, Amazon
Minisforum MS-S1 Max (Ryzen AI Max+ 395)128 GB256 GB/szephyr:141b, dbrx:132b, mistral-medium-3.5:128b +383 morefrom $2,959Minisforum, Amazon

Want a single GPU instead? See Compare GPUs or What fits my GPU? For datacenter cards (H100, B200, MI300X), each GPU page has a "How to buy" section with quote, cloud-rental, and integrator options.