Autor: Jakub Rusinowski · Ostatnia aktualizacja: 17 marca 2025
Najnowszy mały model Mistrala z możliwościami wizji i licencją Apache 2.0. Mistral Small 3.1 24B posiada okno kontekstowe 128k (4× większe niż poprzednik), multimodalną analizę obrazów i pełne zastosowanie komercyjne — jednocześnie przewyższając Gemma 3 27B w większości benchmarków.
| Licence | What it permits | Applies to |
|---|---|---|
Apache-2.0 | Commercial use permitted Commercial use permitted. No usage restrictions beyond attribution. | Mistral Small 3.1 24B |
| Mistral Small 3.1 24B | Min 15 GB VRAM · Q4_K_M · 128,000 ctx · ollama run mistral-small3.1 |
The cheapest GPU that runs Mistral Small 3.1 locally (min 15 GB VRAM) is the AMD Radeon RX 9060 XT 16GB (16 GB).
Install Ollama then run: ollama run mistral-small3.1
Minimum VRAM: 15 GB. For best results use Q4_K_M quantization.
Mistral Small 3.1 needs about 15 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mistral Small 3.1 24B (15 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Yes — Mistral Small 3.1 runs on an RTX 4090 (24 GB) and other 24 GB cards such as the RTX 3090. Smaller variants also fit comfortably on 8–16 GB GPUs at Q4_K_M.
Q4_K_M is the best balance of quality and VRAM for Mistral Small 3.1 in most cases. Choose Q8_0 for near-lossless quality if you have spare VRAM, or smaller quants (Q3/Q2) only when memory is tight.
Install Ollama, then run: ollama run mistral-small3.1. This downloads Mistral Small 3.1 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.