Check my GPU

LLMs ·

Mistral Small 4 (119B-A6B)

Parameters
119B (6.0B active)
Architecture
Mixture of experts
Max context
1,024K tokens
License
apache-2.0
Released
2026-03

How to run it

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/Mistral-Small-4-119B-2603-GGUF (opens in a new tab)

ollama run hf.co/unsloth/Mistral-Small-4-119B-2603-GGUF

Original weights · Hugging Face

Full-precision files from Mistral AI, for fine-tuning, vLLM, Transformers.

huggingface.co/mistralai/Mistral-Small-4-119B-2603 (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Mistral AI. The weights themselves download from Hugging Face.

github.com/mistralai/mistral-inference (opens in a new tab)

git clone https://github.com/mistralai/mistral-inference

Mistral AI’s official inference code.

Links checked 7 days ago against Hugging Face, Ollama and GitHub.

Memory needed

Weights plus KV cache and runtime overhead. Leave a little extra free for the operating system and other apps.

KV cache: latent (MLA) KV cache.

Quantization Quality Weights Total at 8K context Total at 32K context Download
Q2_K Low 47.8 GB 48.5 GB 49.1 GB GGUF (UD-Q2_K_XL) (opens in a new tab)
Q3_K_M Low 58.5 GB 59.3 GB 59.9 GB GGUF · folder (opens in a new tab)
Q4_K_M Good 72.8 GB 73.6 GB 74.2 GB GGUF · folder (opens in a new tab)
Q5_K_M High 84.8 GB 85.6 GB 86.1 GB GGUF · folder (opens in a new tab)
Q6_K High 97.9 GB 98.7 GB 99.3 GB GGUF · folder (opens in a new tab)
Q8_0 Very high 127 GB 127 GB 128 GB GGUF · folder (opens in a new tab)
F16 Full 239 GB 240 GB 240 GB GGUF · folder (opens in a new tab) Original weights (opens in a new tab)

Best hardware for Mistral Small 4 (119B-A6B)

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at Q4_K_M.

Grade · points Hardware Quant Memory Speed Fit
90 ptsExcellent (S) · 90 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M2 Ultra (192 GB) Q6_K 110 GB / 144 GB 48.9 tok/s Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 13.7/15 Apple M3 Ultra (256 GB) Q6_K 114 GB / 192 GB 50.1 tok/s Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Max (128 GB) Q4_K_M 81.3 GB / 96.0 GB 48.1 tok/s Runs well
89 ptsExcellent (S) · 89 of 100 points: Model quality 34.5/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 15.0/15 NVIDIA RTX PRO 6000 Blackwell Q4_K_M 78.4 GB / 96.0 GB 183 tok/s Runs well
86 ptsExcellent (S) · 86 of 100 points: Model quality 34.5/45, Memory fit 25.0/25, Speed 12.5/15, Memory use 15.0/15 NVIDIA GB10 (128 GB) Q4_K_M 82.8 GB / 115 GB 27.9 tok/s Runs well
85 ptsExcellent (S) · 85 of 100 points: Model quality 34.5/45, Memory fit 25.0/25, Speed 11.3/15, Memory use 15.0/15 AMD Ryzen AI Max+ 395 (128 GB) Q4_K_M 81.3 GB / 96.0 GB 22.6 tok/s Runs well
83 ptsGreat (A) · 83 of 100 points: Model quality 35.9/45, Memory fit 25.0/25, Speed 15.0/15, Memory use 7.8/15 Apple M3 Ultra (512 GB) Q6_K 129 GB / 384 GB 50.1 tok/s Runs well
65 ptsGood (B) · 65 of 100 points: Model quality 25.4/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M1 Max (64 GB) Q2_K 52.4 GB / 48.0 GB 49.2 tok/s Runs with offload
65 ptsGood (B) · 65 of 100 points: Model quality 25.4/45, Memory fit 10.0/25, Speed 15.0/15, Memory use 15.0/15 Apple M4 Max (64 GB) Q2_K 52.4 GB / 48.0 GB 67.1 tok/s Runs with offload
56 ptsUsable (C) · 56 of 100 points: Model quality 25.4/45, Memory fit 4.0/25, Speed 12.5/15, Memory use 15.0/15 NVIDIA GeForce RTX 5090 Q2_K 50.1 GB / 32.0 GB 27.8 tok/s Heavy offload

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.