DeepSeek on Apple M3
Can I run DeepSeek-R1 671B-A37B on an Mac Studio M3 Ultra 256GB?
Not at Q4_K_M — it needs 380.1 GB against 192.0 GB available. You would need 2 of these cards.
Won't fit
380.1 GB of 192.0 GB · 198%0395 GB
Weights
379.0 GB
KV cache
0.5 GB
Runtime overhead
0.6 GB
Over the limit
188.1 GB
Short by 188.1 GB. You can run it with 30 of 61 layers on the Mac Studio M3 Ultra 256GB and the rest in system RAM, at roughly 3.10 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation3.10tok/s
Prompt processing324tok/s
Max context0tokens
KV per 1K tokens0GB
Every quantisation of DeepSeek-R1 671B-A37B on a Mac Studio M3 Ultra 256GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 1249.8 GB | 1250.9 GB | Won't fit | — | 0.61 |
| INT8 / W8A8 | 8.50 | 663.6 GB | 664.7 GB | Won't fit | — | 1.33 |
| Q8_0 (GGUF) | 8.50 | 663.6 GB | 664.7 GB | Won't fit | — | 1.33 |
| FP8 (E4M3) | 8.00 | 624.9 GB | 626.0 GB | Won't fit | — | 1.44 |
| Q6_K | 6.56 | 512.4 GB | 513.5 GB | Won't fit | — | 1.90 |
| Q5_K_M | 5.67 | 442.9 GB | 444.0 GB | Won't fit | — | 2.41 |
| Q5_K_S | 5.52 | 431.2 GB | 432.3 GB | Won't fit | — | 2.53 |
| Q4_K_M | 4.85 | 379.0 GB | 380.1 GB | Won't fit | — | 3.10 |
| Q4_K_S | 4.58 | 358.0 GB | 359.1 GB | Won't fit | — | 3.46 |
| Q4_0 | 4.55 | 355.6 GB | 356.7 GB | Won't fit | — | 3.48 |
| AWQ 4-bit | 4.25 | 334.5 GB | 335.6 GB | Won't fit | — | 3.92 |
| GPTQ 4-bit | 4.25 | 334.5 GB | 335.6 GB | Won't fit | — | 3.92 |
| MXFP4 | 4.25 | 334.5 GB | 335.6 GB | Won't fit | — | 3.92 |
| IQ4_XS | 4.25 | 332.3 GB | 333.4 GB | Won't fit | — | 4.06 |
| Q3_K_M | 3.91 | 305.8 GB | 306.9 GB | Won't fit | — | 4.84 |
| IQ3_M | 3.70 | 289.4 GB | 290.5 GB | Won't fit | — | 5.47 |
| IQ3_XXS | 3.06 | 239.6 GB | 240.7 GB | Won't fit | — | 9.16 |
| Q2_K | 2.63 | 206.1 GB | 207.2 GB | Won't fit | — | 17.5 |
| IQ2_XXS | 2.06 | 161.7 GB | 162.8 GB | Runs comfortably | 160K | 36.0 |
| IQ1_M | 1.75 | 137.5 GB | 138.6 GB | Runs comfortably | 160K | 40.9 |