Mistral AI · 8B · 密集（Dense）
Mistral's efficient 8B model 看看你的 GPU 或 Mac 跑不跑得動 Ministral 8B——最低 4.5 GB，建議 7.5 GB。
2024-1032K context
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 3.1 GB | low | — |
| Q3_K_M | 3 | 4.1 GB | moderate | — |
| Q4_K_M | 4 | 4.6 GB | good | — |
| Q5_K_M | 5 | 5.6 GB | good | — |
| Q6_K | 6 | 6.6 GB | excellent | — |
| Q8_0 | 8 | 8.7 GB | excellent | — |
| F16 | 16 | 16.9 GB | lossless | — |
関于这個模型
This model requires Ollama 0.13.1, which is currently in pre-release.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware.
The Ministral 3 models offer the following capabilities:
- Vision: Enables the model to analyze images and provide insights based on visual content, in addition to text.
- Multilingual: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
- System Prompt: Maintains strong adherence and support for system prompts.
- Agentic: Offers best-in-class agentic capabilities with native function calling and JSON outputting.
- Edge-Optimized: Delivers best-in-class performance at a small scale, deployable anywhere.
- Apache 2.0 License: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
- Large Context Window: Supports a 256k context window.
Ministral 14B
Ministral 8B
Ministral 3B
Can I run Ministral 8B locally?
- Can I run Ministral 8B locally?
- Ministral 8B needs about 4.5 GB of memory at a minimum and 7.5 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does Ministral 8B need?
- At Q4_K_M, Ministral 8B uses about 4.6 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.