Ministral — Local AI Model by Mistral AI

作者： Jakub Rusinowski · 最后更新： 2024年10月16日

Superseded model. Ministral has been superseded by Mistral Small 4. This page is kept for reference; the newer family is a better starting point. View Mistral Small 4 →

Mistral AI针对资源受限环境的轻量级模型系列。Ministral 8B的推理任务表现远超其规格，在6 GB VRAM GPU上即可运行。Ministral 3B专为手机和边缘设备设计。

Licence

Licence	What it permits	Applies to
`Mistral Research`	Research / non-commercial only Research / non-commercial only — this licence does NOT permit shipping a commercial product.	Ministral 3B, Ministral 8B

Hardware Requirements

Ministral 3B	Min 3 GB VRAM · Q4_K_M · 32,768 ctx · `ollama run ministral:3b`
Ministral 8B	Min 6 GB VRAM · Q4_K_M · 32,768 ctx · `ollama run ministral:8b`

Recommended GPU

The cheapest GPU that runs Ministral locally (min 3 GB VRAM) is the Intel Arc B570 (10 GB).

联盟营销声明: 本页部分链接为联盟推广链接——如果你通过它们购买，LLM Configurator 可能会获得佣金，而你无需支付任何额外费用。作为亚马逊联盟成员（Amazon Associate），LLM Configurator 会从符合条件的购买中获得收益。

Intel Arc B570 10GB

10 GB VRAM · 150 W board power

2026年价格波动较大——请以当前商品页价格为准。

在亚马逊查看价格

How to Run Locally

Install Ollama then run: ollama run ministral:3b

Minimum VRAM: 3 GB. For best results use Q4_K_M quantization.

Ministral — Frequently Asked Questions

How much VRAM does Ministral need?

Ministral needs about 3 GB VRAM at Q4_K_M quantization for its smallest variant. Variants: Ministral 3B (3 GB, Q4_K_M); Ministral 8B (6 GB, Q4_K_M). On Apple Silicon, unified memory counts toward this requirement.

Can I run Ministral on an RTX 4090 (24 GB)?

Yes — Ministral 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 Ministral?

Q4_K_M is the best balance of quality and VRAM for Ministral 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 Ministral with Ollama?

Install Ollama, then run: ollama run ministral:3b. This downloads Ministral and starts a local, OpenAI-compatible endpoint — no internet connection is needed after the initial download.