Best home rig for DeepSeek R1 Distill 70B

Older model. For current picks see 2025–2026 models.

Real, measured generation speeds for DeepSeek R1 Distill 70B on home hardware, fastest first. Different quants/engines aren't directly comparable.

Build	Quant	Engine	tok/s	Cost
Framework Desktop (AMD Strix Halo) mainboard	Ollama default	Ollama (CPU only, iGPU not used)	2.43		source

Rent before you buy: try this model on a cloud GPU for a few dollars first: Runpod (referral link; sign up with Google to get the new-user bonus)

FAQ

What is the fastest measured hardware for DeepSeek R1 Distill 70B?

Framework Desktop (AMD Strix Halo) mainboard: 2.43 tok/s generation (Ollama (CPU only, iGPU not used), Ollama default), from https://github.com/geerlingguy/ai-benchmarks/issues/21.