Yes — with 32.9 GB to spare
Mistral Small 3.2 24B at Q4_K_M fits your Ryzen AI Max+ 395 · 64 GB entirely in unified memory at 8K context, at an estimated 11 tokens per second. There is room for its full 128K window.
Fully in unified memory
8K context
Q4_K_M · 13.3 GB
Apache 2.0
Released Jun 2025
Vision
Apache-2.0, vision-capable, and the most 24 GB-friendly of the 2025 generalists.
The VRAM budget
weights 13.3 GB
Weights 13.3 GB
KV cache @ 8K 1.25 GB
Runtime overhead 0.6 GB
Free 32.9 GB of 48.0 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 23.4 GB | 25.2 GB | 128K | 6.1 | −0.1% ppl | Long context |
| Q6_K | 18.0 GB | 19.9 GB | 128K | 7.9 | −0.4% ppl | Long context |
| Q5_K_M | 15.6 GB | 17.4 GB | 128K | 9.2 | −0.8% ppl | Long context |
| Q4_K_M | 13.3 GB | 15.1 GB | 128K | 11 | −1.9% ppl | Recommended |
| Q3_K_M | 10.7 GB | 12.6 GB | 128K | 13 | −5.4% ppl | Long context |
| Q2_K | 9.2 GB | 11.1 GB | 128K | 16 | −15% ppl | Long context |
Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.
How to run it
$ ollama pull mistral-small:24b $ OLLAMA_CONTEXT_LENGTH=8192 \ ollama run mistral-small:24b
The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.
01Download is 13.3 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02macOS caps what the GPU may wire down at about 48.0 GB of 64 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03There is room to go to the model's full 128K context on this card.