RigsForLLM
MachinesModelsCan I run it?GPUsCompareLearnAbout

Categories

Kinds of machine

  • Apple unified memory
    • Apple Mac Studio (M5 Max, 32-core GPU)
    • Apple Mac Studio (M5 Max, 40-core GPU)
    • Apple Mac Studio (M5 Ultra, 64-core GPU)
    • Apple Mac Studio (M5 Ultra, 80-core GPU)
    • Apple Mac mini (M5 Pro, 16-core GPU)
    • Apple Mac mini (M5 Pro, 20-core GPU)
    • Apple MacBook Pro 14-inch (M5 Max, 32-core GPU)
    • Apple MacBook Pro 14-inch (M5 Max, 40-core GPU)
    • Apple MacBook Pro 16-inch (M5 Max, 32-core GPU)
    • Apple MacBook Pro 16-inch (M5 Max, 40-core GPU)
  • AMD unified memory
    • Framework Desktop (Ryzen AI Max+ 395)
    • Framework Desktop (Ryzen AI Max 385)
    • Framework Desktop (Ryzen AI Max+ PRO 495)
    • GMKtec EVO-X2 (Ryzen AI Max+ 395)
    • Beelink GTR9 Pro (Ryzen AI Max+ 395)
    • Minisforum MS-S1 MAX (Ryzen AI Max+ 395)
    • Corsair AI Workstation 300 (Ryzen AI Max+ 395)
    • HP Z2 Mini G1a (Ryzen AI Max+ PRO 395)
  • NVIDIA GB10
    • NVIDIA DGX Spark
    • Dell Pro Precision with GB10
  • NVIDIA workstation
    • Dell Pro Precision with GB300
    • Dell Pro Max Tower T2 with NVIDIA RTX PRO 6000 Blackwell
  • Single GPU
    • 1x RTX 3090 (used)
    • 1x RTX 5090
    • 1x RTX PRO 6000 Blackwell
  • Multi-GPU
    • 2x RTX 3090 (used)
    • 4x RTX 3090 (used) on EPYC 7003, open frame
    • 2x RTX 5090
    • 2x Radeon RX 7900 XTX
    • 4x Instinct MI50 32GB (used) on EPYC 7003
    • 2x Intel Arc Pro B60
  • Hybrid GPU + RAM
    • RTX 5090 + EPYC 9355P with 768 GB DDR5 (MoE offload)
    • RTX 3090 (used) + 128 GB DDR5 on AM5 (MoE offload)

RigsForLLM

Machines for running open-weight language models on your own hardware, set against the memory each model needs and the speeds people have published.

36 machines · 41 models · 1044 measurements · updated October 2026

Machines

  • Apple unified memory
  • AMD unified memory
  • NVIDIA GB10
  • NVIDIA workstation
  • Single GPU
  • Multi-GPU
  • Hybrid GPU + RAM
  • Every machine →

Reading

  • Why memory bandwidth sets generation speed
  • Quantization: what 4-bit and 8-bit files cost and save
  • Context memory: why long conversations need more RAM
  • Mixture-of-experts models: total versus active parameters
  • Unified memory: how much of it the GPU can use

Tools

  • Can I run it?
  • Models and what runs them
  • GPUs in the builds
  • Comparisons

Prices are approximate: maker list prices for complete machines and maker prices for DIY parts, from the last catalog update. What a shop charges today may differ.

AboutHow we compareContactPrivacy