---
title: MiniMax-M3.1-Flash-Text-3bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniMax-M3.1-Flash-Text-3bit"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniMax-M3.1-Flash-Text-3bit.md"
repository: mlx-community/MiniMax-M3.1-Flash-Text-3bit
last_updated: 2026-10-23
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - minimax_m3_vl
architectures:
  - MiniMaxM3SparseForConditionalGeneration
base_model:
  - MiniMaxAI/MiniMax-M3.1-Flash
base_model_relation: quantized
parameters: 53.3B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 4
stars: 1
tags:
  - moe
  - agent
  - coding
  - mlx
---

# MiniMax-M3.1-Flash-Text-3bit

> MiniMax-M3.1-Flash-Text-3bit - mlx-community 在 ModelScope 开源的模型。mlx-community/MiniMax-M3.1-Flash-Text-3bit

mlx-community/MiniMax-M3.1-Flash-Text-3bit 是 ModelScope 魔搭社区上的 53.3B 参数text-generation模型，采用 other 许可，基于 MiniMaxAI/MiniMax-M3.1-Flash 构建。

- **Repository**: mlx-community/MiniMax-M3.1-Flash-Text-3bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 53.3B
- **Base model**: MiniMaxAI/MiniMax-M3.1-Flash
- **Tags**: moe, agent, coding, mlx
- **Downloads**: 4
- **Stars**: 1
- **Last updated**: 2026-10-23

Source: https://www.modelscope.cn/models/mlx-community/MiniMax-M3.1-Flash-Text-3bit

---

# mlx-community/MiniMax-M3.1-Flash-Text-3bit

This model [mlx-community/MiniMax-M3.1-Flash-Text-3bit](https://huggingface.co/mlx-community/MiniMax-M3.1-Flash-Text-3bit) was converted to MLX format from [MiniMaxAI/MiniMax-M3.1-Flash](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash) using mlx-lm with [ml-explore/mlx-lm#2003](https://github.com/ml-explore/mlx-lm/pull/2003). Refer to the [original model card](https://huggingface.co/MiniMaxAI/MiniMax-M3.1-Flash) for more details on the model.

This is a text-only conversion. The vision tower is not included.

The original weights were dequantized and then quantized to 3-bit affine with group size 64 (3.5 bits per weight). The router is kept at 8 bits. Peak memory was about 187 GB in a short generation test.

Tested with mlx-lm 0.32.2.

## Use with mlx

```bash
pip install -U mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M3.1-Flash-Text-3bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```