No — not on this device

Mistral Small 4 119B-A6B at Q4_K_M needs 67.7 GB against 14.4 GB usable, and the shortfall of 53.3 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+.

Hardware requirements What hardware do I need to run Mistral Small 4 119B-A6B? →

At Q4_K_M with an 8K context: a 141 GB GPU (H200 SXM) or a 128 GB Mac. Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 66.9 GB
Weights 66.9 GB KV cache @ 8K 0.18 GB Runtime overhead 0.6 GB Over budget 53.3 GB past 14.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 117.8 GB 118.5 GB — ~2.4 −0.1% ppl 104.1 GB over
Q6_K 90.9 GB 91.7 GB — ~3.3 −0.4% ppl 77.3 GB over
Q5_K_M 78.5 GB 79.3 GB — ~3.9 −0.8% ppl 64.9 GB over
Q4_K_M 66.9 GB 67.7 GB — ~4.7 −1.9% ppl 53.3 GB over
Q3_K_M 54.2 GB 54.9 GB — ~6.2 −5.4% ppl 40.5 GB over
Q2_K 46.4 GB 47.2 GB — ~7.6 −15% ppl 32.8 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

terminal
$ llama-server \
    -hf mistralai/Mistral-Small-4-119B-2603:Q4_K_M \
    -c 8192 -ngl 7

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.
See all models for this rig Compare with another model

Related models on a CMP 100-210

ModelTotalTok/s est.
Mistral Small 3.2 24B
23.6B · same family
Q4_K_M · 15.1 GB ~22 CPU offload
gpt-oss 120B
117B MoE · similar size
MXFP4 · 61.4 GB — Won't fit
Nemotron 3 Super 120B-A12B
124B MoE · similar size
Q4_K_M · 70.4 GB — Won't fit
Ling 3.0 Flash 124B-A5B
124B MoE · similar size
Q4_K_M · 70.4 GB — Won't fit
Qwen3.5 122B-A10B
125B MoE · similar size
Q4_K_M · 71.1 GB — Won't fit
Llama 4 Scout 109B-A17B
109B MoE · similar size
Q4_K_M · 63.4 GB — Won't fit
Qwen3.8-Flash-Next 180B-A6B
180B MoE · similar size
Q4_K_M · 102.0 GB — Won't fit

Every model against the CMP 100-210 →

Mistral Small 4 119B-A6B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
67.7 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
67.7 GB — Won't fit
M4 · 16 GB
10.7 GB usable · 120 GB/s
67.7 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
67.7 GB — Won't fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
67.7 GB — Won't fit
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
67.7 GB — Won't fit
DGX Spark · 128 GB
96.0 GB usable · 273 GB/s
67.7 GB 19 Runs great
H200 SXM
139.4 GB usable · 4800 GB/s
67.7 GB 306 Runs great

All 114 devices, by tier →