No — not on this device
Mistral Small 4 119B-A6B at Q4_K_M needs 67.7 GB against 8.8 GB usable, and the shortfall of 58.9 GB is more than 16 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.
Does not fit
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+.
The VRAM budget
weights 66.9 GB
Weights 66.9 GB
KV cache @ 8K 0.18 GB
Runtime overhead 0.6 GB
Over budget 58.9 GB past 8.8 GB
Quantisation ladder
| Quant | Weights | Total @ 8K | Max context | Tok/s | Quality | Fit |
|---|---|---|---|---|---|---|
| Q8_0 | 117.8 GB | 118.5 GB | — | ~2.3 | −0.1% ppl | 109.7 GB over |
| Q6_K | 90.9 GB | 91.7 GB | — | ~3.1 | −0.4% ppl | 82.9 GB over |
| Q5_K_M | 78.5 GB | 79.3 GB | — | ~3.6 | −0.8% ppl | 70.5 GB over |
| Q4_K_M | 66.9 GB | 67.7 GB | — | ~4.3 | −1.9% ppl | 58.9 GB over |
| Q3_K_M | 54.2 GB | 54.9 GB | — | ~5.5 | −5.4% ppl | 46.1 GB over |
| Q2_K | 46.4 GB | 47.2 GB | — | ~6.6 | −15% ppl | 38.4 GB over |
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-server \
-hf mistralai/Mistral-Small-4-119B-2603:Q4_K_M \
-c 8192 -ngl 4
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.
03If it falls back to CPU silently, drop the context first, then step down a quantisation.