Can Apple M3 Ultra run DeepSeek R1 671B?
Yes. Measured 19.89 tok/s generation (llama.cpp; source).
Every measured result for DeepSeek R1 671B on Apple M3 Ultra
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| Mac Studio M3 Ultra 512GB (Geerling test) | llama.cpp | 19.89 | source | |
| Mac Studio M3 Ultra, 512 GB | Q4 | MLX | 18.43 | source ⚠ unchecked |
Memory: Apple M3 Ultra has 512 GB. DeepSeek R1 671B weights are about 410.5 GB at Q4_K_M (671B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for DeepSeek R1 671B: best home rig for DeepSeek R1 671B.
DeepSeek R1 671B on other hardware: RTX 3090
Other models measured on Apple M3 Ultra: Mistral Medium 3.5 128B · Muse Spark Open 816B-A42B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run DeepSeek R1 671B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.