Mistral on Apple M3
Can I run Mistral NeMo 12B on an Mac Studio M3 Ultra 256GB?
Yes. Mistral NeMo 12B at Q4_K_M uses 8.8 GB of the 192.0 GB available on a Mac Studio M3 Ultra 256GB, and runs at about 61.0 tokens per second. You can push the context to 128K.
Runs comfortably
8.8 GB of 192.0 GB · 5%0192 GB
Weights
7.0 GB
KV cache
1.3 GB
Runtime overhead
0.5 GB
Mistral NeMo 12B at Q4_K_M leaves 183.2 GB spare on a Mac Studio M3 Ultra 256GB. There is room to raise the context length or move up a quantisation level.
Generation61.0tok/s
Prompt processing977tok/s
Max context128Ktokens
KV per 1K tokens0GB
Every quantisation of Mistral NeMo 12B 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 | 22.8 GB | 24.6 GB | Runs comfortably | 128K | 20.1 |
| INT8 / W8A8 | 8.50 | 11.8 GB | 13.6 GB | Runs comfortably | 128K | 37.7 |
| Q8_0 (GGUF) | 8.50 | 11.8 GB | 13.6 GB | Runs comfortably | 128K | 37.7 |
| FP8 (E4M3) | 8.00 | 11.4 GB | 13.2 GB | Runs comfortably | 128K | 39.0 |
| Q6_K | 6.56 | 9.4 GB | 11.1 GB | Runs comfortably | 128K | 46.9 |
| Q5_K_M | 5.67 | 8.1 GB | 9.9 GB | Runs comfortably | 128K | 53.6 |
| AWQ 4-bit | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 54.8 |
| GPTQ 4-bit | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 54.8 |
| MXFP4 | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 54.8 |
| Q5_K_S | 5.52 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 55.0 |
| Q4_K_M | 4.85 | 7.0 GB | 8.8 GB | Runs comfortably | 128K | 61.0 |
| Q4_K_S | 4.58 | 6.7 GB | 8.5 GB | Runs comfortably | 128K | 63.8 |
| Q4_0 | 4.55 | 6.6 GB | 8.4 GB | Runs comfortably | 128K | 64.2 |
| IQ4_XS | 4.25 | 6.3 GB | 8.0 GB | Runs comfortably | 128K | 67.7 |
| Q3_K_M | 3.91 | 5.8 GB | 7.6 GB | Runs comfortably | 128K | 72.1 |
| IQ3_M | 3.70 | 5.6 GB | 7.3 GB | Runs comfortably | 128K | 75.2 |
| IQ3_XXS | 3.06 | 4.7 GB | 6.5 GB | Runs comfortably | 128K | 86.3 |
| Q2_K | 2.63 | 4.2 GB | 6.0 GB | Runs comfortably | 128K | 95.8 |
| IQ2_XXS | 2.06 | 3.5 GB | 5.3 GB | Runs comfortably | 128K | 112 |
| IQ1_M | 1.75 | 3.1 GB | 4.9 GB | Runs comfortably | 128K | 124 |