Mistral Small 3.2 — lokalny model AI od Mistral AI
Autor: Jakub Rusinowski · Ostatnia aktualizacja:
A reliability release rather than a capability one. Same 24B architecture as Small 3.1, with instruction-following, function-calling robustness and output stability fixed — Arena Hard more than doubles (19.56% to 43.10%) and the infinite-repetition rate halves. If you were running 3.1, this is a drop-in upgrade with no new hardware cost.
Warianty
Najmniejszy wariant Mistral Small 3.2 potrzebuje około 15 GB VRAM przy Q4_K_M — skwantyzowane wagi plus narzut frameworka, bez pamięci podręcznej KV.
| Model | VRAM przy Q4 | VRAM | Kontekst | Uruchom |
|---|---|---|---|---|
| Mistral Small 3.2 24B → 24B | ~15 GB | 131,072 | ollama run mistral-small:24b |
Pamięć to skwantyzowane wagi plus narzut przy Q4_K_M, liczone tym samym silnikiem co sprawdzarka GPU i VRAM.
Jak uruchomić Mistral Small 3.2 lokalnie
Zainstaluj Ollama, a potem pobierz tag.
ollama run mistral-small:24bWybierz rozmiar powyżej, aby zobaczyć jego VRAM, szacowaną szybkość i polecenie instalacji.
Licencja
Commercial use permitted. No usage restrictions beyond attribution.
Dotyczy: Mistral Small 3.2 24BPolecane GPU
Najtańsze GPU z naszego katalogu, które uruchomi Mistral Small 3.2 lokalnie (min. 15 GB VRAM), to AMD Radeon RX 7900 XT (20 GB).
Czy uruchomię Mistral Small 3.2 na moim GPU?
- Mistral Small 3.2 na AMD Radeon RX 7800 XT
- Mistral Small 3.2 na AMD Radeon RX 7900 XT
- Mistral Small 3.2 na AMD Radeon RX 7900 XTX
- Mistral Small 3.2 na AMD Radeon RX 9060 XT 16GB
- Mistral Small 3.2 na AMD Radeon RX 9060 XT 8GB
- Mistral Small 3.2 na AMD Radeon RX 9070
- Mistral Small 3.2 na AMD Radeon RX 9070 XT
- Mistral Small 3.2 na Apple M1
- Mistral Small 3.2 na Apple M1 Pro
- Mistral Small 3.2 na Apple M2
- Mistral Small 3.2 na Apple M2 Pro
- Mistral Small 3.2 na Apple M3
- Mistral Small 3.2 na Apple M4
- Mistral Small 3.2 na Apple M4 Pro
- Mistral Small 3.2 na Apple M5
- Mistral Small 3.2 na Intel Arc B570
- Mistral Small 3.2 na Intel Arc B580
- Mistral Small 3.2 na NVIDIA GeForce RTX 3060 (12GB)
- Mistral Small 3.2 na NVIDIA GeForce RTX 3070
- Mistral Small 3.2 na NVIDIA GeForce RTX 3070 Ti
- Mistral Small 3.2 na NVIDIA GeForce RTX 3080 (10GB)
- Mistral Small 3.2 na NVIDIA GeForce RTX 3090
- Mistral Small 3.2 na NVIDIA GeForce RTX 4060
- Mistral Small 3.2 na NVIDIA GeForce RTX 4060 Ti 16GB
- Mistral Small 3.2 na NVIDIA GeForce RTX 4070
- Mistral Small 3.2 na NVIDIA GeForce RTX 4070 Super
- Mistral Small 3.2 na NVIDIA GeForce RTX 4070 Ti
- Mistral Small 3.2 na NVIDIA GeForce RTX 4070 Ti Super
- Mistral Small 3.2 na NVIDIA GeForce RTX 4080
- Mistral Small 3.2 na NVIDIA GeForce RTX 4080 Super
- Mistral Small 3.2 na NVIDIA GeForce RTX 4090
- Mistral Small 3.2 na NVIDIA GeForce RTX 5060
- Mistral Small 3.2 na NVIDIA GeForce RTX 5060 Ti 16GB
- Mistral Small 3.2 na NVIDIA GeForce RTX 5060 Ti 8GB
- Mistral Small 3.2 na NVIDIA GeForce RTX 5070
- Mistral Small 3.2 na NVIDIA GeForce RTX 5070 Ti
- Mistral Small 3.2 na NVIDIA GeForce RTX 5080
- Mistral Small 3.2 na NVIDIA GeForce RTX 5090
Mistral Small 3.2 — najczęściej zadawane pytania
How much VRAM does Mistral Small 3.2 need?
Mistral Small 3.2 needs about 15 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Mistral Small 3.2 24B (15 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.
Can I run Mistral Small 3.2 on an RTX 4090 (24 GB)?
Yes — Mistral Small 3.2 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.
What quantization should I use for Mistral Small 3.2?
Q4_K_M is the best balance of quality and VRAM for Mistral Small 3.2 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.
How do I run Mistral Small 3.2 with Ollama?
Install Ollama, then run: ollama run mistral-small:24b. This downloads Mistral Small 3.2 and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.