Yes — with 122.7 GB to spare

Mistral Small 4 119B-A6B at Q4_K_M fits your Instinct MI300X entirely on the GPU at 8K context, at an estimated 338 tokens per second. There is room for its full 256K window.

Fully on GPU 8K context Q4_K_M · 66.9 GB Apache 2.0 Released 17 Mar 2026 Vision Not in the Ollama library

Instruct, reasoning, vision and code in one 119B MoE. A latent KV cache (320 wide) keeps context cheap; the weights still want 64 GB+.

What hardware do I need for Mistral Small 4 119B-A6B? →

The VRAM budget

weights 66.9 GB

Weights 66.9 GB KV cache @ 8K 0.18 GB Runtime overhead 0.6 GB Free 122.7 GB of 190.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	117.8 GB	118.5 GB	256K	192	−0.1% ppl	Long context
Q6_K	90.9 GB	91.7 GB	256K	249	−0.4% ppl	Long context
Q5_K_M	78.5 GB	79.3 GB	256K	288	−0.8% ppl	Long context
Q4_K_M	66.9 GB	67.7 GB	256K	338	−1.9% ppl	Recommended
Q3_K_M	54.2 GB	54.9 GB	256K	417	−5.4% ppl	Long context
Q2_K	46.4 GB	47.2 GB	256K	487	−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. This model uses multi-head latent attention, so its cache is a compressed latent rather than full K and V.

How to run it

llama.cpp LM Studio vLLM

terminal

$ llama-server \
    -hf mistralai/Mistral-Small-4-119B-2603:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

01Download is 66.9 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 256K context on this card.

See all models for this rig Compare with another model