---
title: Ministral-3-8B-Base-2512-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Ministral-3-8B-Base-2512-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Ministral-3-8B-Base-2512-4bit.md"
repository: mlx-community/Ministral-3-8B-Base-2512-4bit
last_updated: 2026-07-18
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - mistral3
architectures:
  - Mistral3ForConditionalGeneration
base_model:
  - mistralai/Ministral-3-8B-Base-2512
base_model_relation: quantized
parameters: 1.7B
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - es
  - de
  - it
  - pt
  - nl
  - zh
  - ja
  - ko
  - ar
downloads: 29
stars: 0
tags:
  - mistral-common
  - mlx
  - ministral
  - ministral-3
  - vision-language
  - multimodal
  - quantized
  - edge
  - 4-bit
  - base-model
---

# Ministral-3-8B-Base-2512-4bit

> Ministral-3-8B-Base-2512-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/Ministral-3-8B-Base-2512-4bit

mlx-community/Ministral-3-8B-Base-2512-4bit 是 ModelScope 魔搭社区上的 1.7B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 mistralai/Ministral-3-8B-Base-2512 构建。

- **Repository**: mlx-community/Ministral-3-8B-Base-2512-4bit
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 1.7B
- **Base model**: mistralai/Ministral-3-8B-Base-2512
- **Tags**: mistral-common, mlx, ministral, ministral-3, vision-language, multimodal, quantized, edge, 4-bit, base-model
- **Downloads**: 29
- **Stars**: 0
- **Last updated**: 2026-07-18

Source: https://www.modelscope.cn/models/mlx-community/Ministral-3-8B-Base-2512-4bit

---

# mlx-community/Ministral-3-8B-Base-2512-4bit

This is, **Ministral 3 8B Base 2512** is a vision-language model: a text backbone paired
with a vision encoder, supporting image understanding alongside text. This is
the **base pre-trained** checkpoint — not instruction- or chat-tuned. For
chat/instruction-following use cases, use the
[Instruct variant](https://huggingface.co/mlx-community/Ministral-3-8B-Instruct-2512-4bit)
instead; this base checkpoint is intended for custom post-training/fine-tuning.

> **Community note.** Structural check confirms the vision tower and
> multimodal projector were carried over intact (not dropped, which is a real
> failure mode for text-only conversion tools on vision-language models).
> Functional check confirms both text-only and image+text generation produce
> coherent output. Converted and verified by a single maintainer running
> local MLX tooling -- not independently reviewed by anyone else; please open
> a discussion if you hit anything unexpected.

This is an MLX conversion of [`mistralai/Ministral-3-8B-Base-2512`](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512),
converted with [mlx-vlm](https://github.com/Blaizzy/mlx-vlm). Refer to the
[original model card](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512) for the full
description, capabilities, and license terms.

## Heads up

- **Base model, not instruct-tuned** — expect raw completion behavior, not
  chat-following. Don't expect it to follow instructions well.
- **Vision retained at full precision** — only the language backbone is
  quantized; the vision tower and multimodal projector are untouched bf16,
  per mlx-vlm's standard policy of not quantizing multimodal modules.
- **Output size on disk: 6.44GB**

## Provenance

- Source: [`mistralai/Ministral-3-8B-Base-2512`](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512) (BF16)
- Language model layers: **4-bit** affine quantization, group_size=64
- Vision tower + multimodal projector: kept at full precision (not quantized)
- Blended average: **5.745 bits per weight** across all parameters

## Ministral 3 family

| Model | Type | mlx-community (4-bit) |
|---|---|---|
| Ministral 3 3B Base 2512 | Base pre-trained | [mlx-community/Ministral-3-3B-Base-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-3B-Base-2512-4bit) |
| Ministral 3 3B Instruct 2512 | Instruct post-trained | [mlx-community/Ministral-3-3B-Instruct-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-3B-Instruct-2512-4bit) |
| Ministral 3 3B Reasoning 2512 | Reasoning capable | [mlx-community/Ministral-3-3B-Reasoning-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-3B-Reasoning-2512-4bit) |
| **Ministral 3 8B Base 2512** | **Base pre-trained** | [mlx-community/Ministral-3-8B-Base-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-8B-Base-2512-4bit) |
| Ministral 3 8B Instruct 2512 | Instruct post-trained | [mlx-community/Ministral-3-8B-Instruct-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-8B-Instruct-2512-4bit) |
| Ministral 3 8B Reasoning 2512 | Reasoning capable | [mlx-community/Ministral-3-8B-Reasoning-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-8B-Reasoning-2512-4bit) |
| Ministral 3 14B Base 2512 | Base pre-trained | [mlx-community/Ministral-3-14B-Base-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-14B-Base-2512-4bit) |
| Ministral 3 14B Instruct 2512 | Instruct post-trained | [mlx-community/Ministral-3-14B-Instruct-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-14B-Instruct-2512-4bit) |
| Ministral 3 14B Reasoning 2512 | Reasoning capable | [mlx-community/Ministral-3-14B-Reasoning-2512-4bit](https://huggingface.co/mlx-community/Ministral-3-14B-Reasoning-2512-4bit) |

## Use with mlx

```bash
pip install -U mlx-vlm
```

```bash
python -m mlx_vlm.generate --model mlx-community/Ministral-3-8B-Base-2512-4bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
```

For text-only prompts, omit `--image`.

## License

Apache 2.0 — see the [original model card](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512) for
the full license text and any usage terms.