---
title: Devstral-Small-2-24B-Instruct-2512-8bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit.md"
repository: mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit
last_updated: 2026-07-05
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - mistral3
architectures:
  - Mistral3ForConditionalGeneration
base_model:
  - mistralai/Devstral-Small-2-24B-Instruct-2512
base_model_relation: quantized
parameters: 7.6B
tensor_type:
  - U32
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 157
stars: 0
tags:
  - mlx
  - mistral3
  - mistral-common
  - safetensors
  - 8-bit
---

# Devstral-Small-2-24B-Instruct-2512-8bit

> Devstral-Small-2-24B-Instruct-2512-8bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit

mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit 是 ModelScope 魔搭社区上的 7.6B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 mistralai/Devstral-Small-2-24B-Instruct-2512 构建。

- **Repository**: mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 7.6B
- **Base model**: mistralai/Devstral-Small-2-24B-Instruct-2512
- **Tags**: mlx, mistral3, mistral-common, safetensors, 8-bit
- **Downloads**: 157
- **Stars**: 0
- **Last updated**: 2026-07-05

Source: https://www.modelscope.cn/models/mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit

---

# mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit

This model was converted to MLX format from [mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512) at revision `c599e8e56f3f9110e97f0dc0450ce248e3334d84`.

It was generated from the current `mlx-vlm` source checkout on the JarvisLabs conversion instance.

## Use with mlx-vlm

```bash
pip install -U mlx-vlm
mlx_vlm.generate --model mlx-community/Devstral-Small-2-24B-Instruct-2512-8bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```