Mistral on AMD Strix Halo
Can I run Mistral NeMo 12B on an Ryzen AI Max+ 395 128GB?
Yes. Mistral NeMo 12B at Q4_K_M uses 8.8 GB of the 96.0 GB available on a Ryzen AI Max+ 395 128GB, and runs at about 17.5 tokens per second. You can push the context to 128K.
Runs comfortably
8.8 GB of 96.0 GB · 9%096 GB
Weights
7.0 GB
KV cache
1.3 GB
Runtime overhead
0.5 GB
Mistral NeMo 12B at Q4_K_M leaves 87.2 GB spare on a Ryzen AI Max+ 395 128GB. There is room to raise the context length or move up a quantisation level.
Generation17.5tok/s
Prompt processing857tok/s
Max context128Ktokens
KV per 1K tokens0GB
Every quantisation of Mistral NeMo 12B on a Ryzen AI Max+ 395 128GB
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 | 5.73 |
| INT8 / W8A8 | 8.50 | 11.8 GB | 13.6 GB | Runs comfortably | 128K | 10.8 |
| Q8_0 (GGUF) | 8.50 | 11.8 GB | 13.6 GB | Runs comfortably | 128K | 10.8 |
| FP8 (E4M3) | 8.00 | 11.4 GB | 13.2 GB | Runs comfortably | 128K | 11.1 |
| Q6_K | 6.56 | 9.4 GB | 11.1 GB | Runs comfortably | 128K | 13.4 |
| Q5_K_M | 5.67 | 8.1 GB | 9.9 GB | Runs comfortably | 128K | 15.4 |
| AWQ 4-bit | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 15.7 |
| GPTQ 4-bit | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 15.7 |
| MXFP4 | 4.25 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 15.7 |
| Q5_K_S | 5.52 | 7.9 GB | 9.7 GB | Runs comfortably | 128K | 15.8 |
| Q4_K_M | 4.85 | 7.0 GB | 8.8 GB | Runs comfortably | 128K | 17.5 |
| Q4_K_S | 4.58 | 6.7 GB | 8.5 GB | Runs comfortably | 128K | 18.3 |
| Q4_0 | 4.55 | 6.6 GB | 8.4 GB | Runs comfortably | 128K | 18.4 |
| IQ4_XS | 4.25 | 6.3 GB | 8.0 GB | Runs comfortably | 128K | 19.5 |
| Q3_K_M | 3.91 | 5.8 GB | 7.6 GB | Runs comfortably | 128K | 20.7 |
| IQ3_M | 3.70 | 5.6 GB | 7.3 GB | Runs comfortably | 128K | 21.6 |
| IQ3_XXS | 3.06 | 4.7 GB | 6.5 GB | Runs comfortably | 128K | 24.9 |
| Q2_K | 2.63 | 4.2 GB | 6.0 GB | Runs comfortably | 128K | 27.7 |
| IQ2_XXS | 2.06 | 3.5 GB | 5.3 GB | Runs comfortably | 128K | 32.5 |
| IQ1_M | 1.75 | 3.1 GB | 4.9 GB | Runs comfortably | 128K | 36.0 |