Yes, just — 10.7 GB spare

Mistral Small 4 119B-A6B at Q4_K_M fits your H100 SXM entirely on the GPU at 8K context, at an estimated 213 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+.

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 Free 10.7 GB of 78.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 117.8 GB 118.5 GB — ~6.2 −0.1% ppl 40.1 GB over
Q6_K 90.9 GB 91.7 GB — ~17 −0.4% ppl 13.3 GB over
Q5_K_M 78.5 GB 79.3 GB — ~110 −0.8% ppl 0.9 GB over
Q4_K_M 66.9 GB 67.7 GB 256K 213 −1.9% ppl Recommended
Q3_K_M 54.2 GB 54.9 GB 256K 264 −5.4% ppl Long context
Q2_K 46.4 GB 47.2 GB 256K 308 −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

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.
03Only 10.7 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 256K context.
See all models for this rig Compare with another model

Related models on an H100 SXM

ModelTotalTok/s est.
Mistral Small 3.2 24B
23.6B · same family
Q4_K_M · 15.1 GB 153 Runs great
gpt-oss 120B
117B MoE · similar size
MXFP4 · 61.4 GB 295 Runs great
Nemotron 3 Super 120B-A12B
124B MoE · similar size
Q4_K_M · 70.4 GB 116 Tight fit
Ling 3.0 Flash 124B-A5B
124B MoE · similar size
Q4_K_M · 70.4 GB 272 Tight fit
Qwen3.5 122B-A10B
125B MoE · similar size
Q4_K_M · 71.1 GB 139 Tight fit
Llama 4 Scout 109B-A17B
109B MoE · similar size
Q4_K_M · 63.4 GB 82 Runs great
Qwen3.8-Flash-Next 180B-A6B
180B MoE · similar size
Q4_K_M · 102.0 GB ~17 CPU offload

Every model against the H100 SXM →

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 →