Yes — with 63.3 GB to spare

Mistral Small 3.2 24B at Q4_K_M fits your H100 SXM entirely on the GPU at 8K context, at an estimated 153 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.

What hardware do I need for Mistral Small 3.2 24B? →

The VRAM budget

weights 13.3 GB

Weights 13.3 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Free 63.3 GB of 78.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	23.4 GB	25.2 GB	128K	87	−0.1% ppl	Long context
Q6_K	18.0 GB	19.9 GB	128K	113	−0.4% ppl	Long context
Q5_K_M	15.6 GB	17.4 GB	128K	130	−0.8% ppl	Long context
Q4_K_M	13.3 GB	15.1 GB	128K	153	−1.9% ppl	Recommended
Q3_K_M	10.7 GB	12.6 GB	128K	189	−5.4% ppl	Long context
Q2_K	9.2 GB	11.1 GB	128K	220	−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 llama.cpp LM Studio vLLM

terminal

$ 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.

See all models for this rig Compare with another model