mistralai/Ministral-3-8B-Instruct-2512-BF16
Parameters8.9B
Context256K
Input → output–
Licenseapache-2.0
PrecisionBF16
ArchitectureMistral3ForConditionalGeneration
ReleasedOct 31, 2025
Downloads42.7K
Based on mistralai/Ministral-3-8B-Base-2512
Other sizes and formats in the family
| Model | Params | Precision | Downloads |
|---|---|---|---|
| mistralai/Ministral-3-14B-Instruct-2512-GGUFgguf | 14B | – | 31.7K |
| mistralai/Ministral-3-14B-Instruct-2512fp8 | 13.9B | F8_E4M3 | 123.7K |
| mistralai/Ministral-3-14B-Base-2512 | 13.9B | BF16 | 3.7K |
| mistralai/Ministral-3-14B-Instruct-2512-BF16 | 13.9B | BF16 | 97K |
| mistralai/Ministral-3-8B-Instruct-2512fp8 | 8.9B | F8_E4M3 | 114.7K |
| mistralai/Ministral-3-8B-Base-2512 | 8.9B | BF16 | 10.1K |
| mistralai/Ministral-3-8B-Instruct-2512-GGUFgguf | 8B | – | 38.1K |
| mistralai/Ministral-3-3B-Base-2512 | 4.3B | BF16 | 13.9K |
| mistralai/Ministral-3-3B-Instruct-2512-BF16 | 4.3B | BF16 | 49K |
| mistralai/Ministral-3-3B-Instruct-2512fp8 | 3.8B | F8_E4M3 | 107.8K |
| mistralai/Ministral-3-3B-Instruct-2512-GGUFgguf | 3B | – | 37.8K |
| mistralai/Ministral-3-3B-Instruct-2512-ONNXquantized | 3B | – | 509 |
This release in the news
No coverage of this exact release yet.
Recent news about Mistral models
- Oct 12, 2026 · Opinion / analysisU-Space: Uncovering When and Why Uncertainty Arises in Language Models [R][D]
- Oct 12, 2026 · Opinion / analysisQLoRA on ExLlamaV3 Quants - Train @ 2-8bpw
- Oct 11, 2026 · Opinion / analysisEvery Model That Can Be Run On 10-16GB VRAM Ranked
- Oct 11, 2026 · Opinion / analysisLocal Voice Assistant based on Qwen3.5 4B with skills/toolcalling. No dedicated GPU. Local STT+TTS
- Oct 10, 2026 · Research paperSharing AI progress in mathematics
- Oct 8, 2026 · Model releasemistralai/Voxtral-Mini-4B-Realtime-Arabic
- Oct 7, 2026 · Product / feature launchIntroducing Mistral Large 4
- Oct 7, 2026 · Research paperActivation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression