Yes — with 23.3 GB to spare
Mistral Small 3.2 24B at Q4_K_M fits your A100 40 GB entirely on the GPU at 8K context, at an estimated 71 tokens per second. There is room for its full 128K window.
Fully on GPU
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 23.3 GB of 38.4 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 23.4 GB | 25.2 GB | 92K | 40 | −0.1% ppl | Long context |
| Q6_K | 18.0 GB | 19.9 GB | 126K | 52 | −0.4% ppl | Long context |
| Q5_K_M | 15.6 GB | 17.4 GB | 128K | 60 | −0.8% ppl | Long context |
| Q4_K_M | 13.3 GB | 15.1 GB | 128K | 71 | −1.9% ppl | Recommended |
| Q3_K_M | 10.7 GB | 12.6 GB | 128K | 88 | −5.4% ppl | Long context |
| Q2_K | 9.2 GB | 11.1 GB | 128K | 102 | −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.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 128K context on this card.