Mistral Models — Hardware Requirements
17 Mistral models from Mistral AI and the community, from the smallest that runs in 0.3 GB of VRAM up to 127.7B parameters. Every row links to full quantization tables and GPU compatibility.
All Mistral Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| PicoMistral 23M | 24M | 0.3 GB | 1K | ||
| OpenHermes 2.5 Mistral 7B | 7B | 3.5 GB | 33K | ||
| Mistral 7B v0.1 | 7B | 3.5 GB | 33K | ||
| BioMistral 7B | 7B | 3.5 GB | 33K | ||
| Mistral 7B Instruct v0.2 | 7.2B | 3.6 GB | 33K | ||
| Mistral 7B Instruct v0.1 | 7.2B | 3.6 GB | 33K | ||
| Mistral 7B v0.2 | 7.2B | 3.6 GB | 33K | ||
| Mistral 7B Instruct v0.3 | 7.2B | 2.6 GB | 33K | ||
| Mistral Nemo Instruct 2407 | 12.2B | 4.8 GB | 131K | ||
| Mistral Nemo 2407 12B Thinking Claude Gemini GPT5.2 Uncensored HERETIC | 12.2B | 5.9 GB | 1024K | ||
| Mistral Small Instruct 2409 | 22.2B | 10.2 GB | 33K | ||
| Mistral Small 24B Instruct 2501 | 23.6B | 7.8 GB | 33K | ||
| Magistral Small 2506 | 23.6B | 7.2 GB | 41K | ||
| Mistral Small 24B Instruct 2501 Quantized.w8a8 | 23.6B | 10.7 GB | 33K | ||
| Mistral Small 3.2 24B Instruct 2506 | 24.0B | 7.3 GB | 131K | ||
| Mistral Small 3.2 24B Qiskit | 24.0B | 10.9 GB | 131K | ||
| Leanstral 1.5 119B A6B | 119B | 55.6 GB | — | ||
| Mistral Medium 3.5 128B | 127.7B | 55.3 GB | 262K |
How Mistral Compares — Benchmark Rating
Mistral 7B v0.1 is the highest-rated Mistral model with an overall benchmark rating of 53.3/100 — #25 among 73 open models. The top proprietary model, Claude Fable 5 Max, scores 89.9. Click a model to see its full benchmark breakdown.
Claude Fable 5 Max · proprietary89.9
GPT 5.5 · proprietary89.2
GPT 5.6 Sol · proprietary89.2
Claude Fable 5 · proprietary88.6
Claude Opus 4.8 · proprietary88.1
GLM 5.282.7
Inkling79.2
DeepSeek V4 Pro74.3
Qwen3.6 27B74.0
Mistral 7B v0.153.3
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?
- 16 of 18 Mistral models fit in 16 GB of VRAM at some quantization, including Mistral 7B Instruct v0.2, Mistral 7B Instruct v0.3, Mistral Nemo Instruct 2407.
- What is the most popular Mistral model to run locally?
- Mistral 7B Instruct v0.2 is the most downloaded Mistral model in local-friendly quantized formats. It runs from 3.6 GB of VRAM.
- How do Mistral models score on benchmarks?
- Mistral 7B v0.1 leads the family with an overall benchmark rating of 53.3/100, ranking #25 among 73 open models, while the top proprietary model, Claude Fable 5 Max, scores 89.9. See the comparison chart above for the full standings.