Mistral Models — Hardware Requirements

33 Mistral models from Mistral AI and the community, from the smallest that runs in 0.3 GB of VRAM up to 675B parameters. Every row links to full quantization tables and GPU compatibility.

All Mistral Models by Size

ModelParamsContext
PicoMistral 23M24M1K
Ministral 3 3B Reasoning 25124.3B262K
OpenHermes 2.5 Mistral 7B7B33K
BioMistral 7B7B33K
Mistral 7B Instruct v0.27.2B33K
Mistral 7B Instruct v0.17.2B33K
Mistral 7B v0.17.2B33K
Mistral 7B v0.27.2B33K
Hermes 2 Pro Mistral 7B7.2B33K
Mistral 7B v0.37.2B33K
Mistral 7B Instruct v0.37.2B33K
Llava V1.6 Mistral 7B HF7.6B33K
Ministral 8B Instruct 24108.0B33K
Mistral NeMo Minitron 8B Instruct8.4B8K
Mistral Nemo Instruct 240712.2B131K
Mistral Nemo Base 240712.2B131K
Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC12.2B1024K
Ministral 3 14B Reasoning 251213.9B262K
Mistral Small Instruct 240922.2B33K
Mistral Small 24B Instruct 250123.6B33K
Devstral Small 250723.6B131K
Devstral Small 250523.6B131K
Magistral Small 250623.6B41K
Mistral Small 24B Instruct 2501 Quantized.w8a823.6B33K
Mistral Small 3.2 24B Instruct 250624.0B131K
Mistral Small 3.1 24B Instruct 250324.0B131K
Magistral Small 250924.0B131K
Mistral Small 3.2 24B Qiskit24.0B131K
Devstral Small 2 24B Instruct 251224.0B393K
Leanstral 1.5 119B A6B119B—
Mistral Large Instruct 2407122.6B—
Devstral 2 123B Instruct 2512125.0B262K
Mistral Medium 3.5 128B127.7B262K
Mistral Large 3 675B Instruct 2512675B—

How Mistral Compares — Benchmark Rating

Mistral Large Instruct 2411 is the highest-rated Mistral model with an overall benchmark rating of 42.8/100 — #43 among 78 open models. The top proprietary model, Claude Fable 5 (high), scores 87.8. Click a model to see its full benchmark breakdown.

Claude Fable 5 (high) · proprietary87.8
Claude Opus 4.7 · proprietary86.4
Claude Fable 5 Max · proprietary82.4
GPT 6 Astra (high) · proprietary82.4
GPT 6 Astra Max · proprietary82.4
GLM 565.9
Composite of normalized public benchmark scores (methodology) · ■ Mistral · ■ other models

Frequently Asked Questions

How much VRAM do I need to run a Mistral model?
The smallest Mistral model, PicoMistral 23M, runs from 0.3 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which Mistral models can I run on a 16 GB GPU?
28 of 34 Mistral models fit in 16 GB of VRAM at some quantization, including Mistral Small 24B Instruct 2501, Mistral 7B v0.3, Mistral 7B Instruct v0.3.
What is the most popular Mistral model to run locally?
Mistral Small 24B Instruct 2501 is the most downloaded Mistral model in local-friendly quantized formats. It runs from 10.7 GB of VRAM.
How do Mistral models score on benchmarks?
Mistral Large Instruct 2411 leads the family with an overall benchmark rating of 42.8/100, ranking #43 among 78 open models, while the top proprietary model, Claude Fable 5 (high), scores 87.8. See the comparison chart above for the full standings.
Mistral Models — VRAM & Hardware Requirements | llmrun