---
title: GLM-4.7-Flash-6bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/GLM-4.7-Flash-6bit"
md_url: "https://www.modelscope.cn/models/mlx-community/GLM-4.7-Flash-6bit.md"
repository: mlx-community/GLM-4.7-Flash-6bit
last_updated: 2026-01-26
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - glm4_moe_lite
architectures:
  - Glm4MoeLiteForCausalLM
base_model:
  - zai-org/GLM-4.7-Flash
base_model_relation: quantized
parameters: 811.0M
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 78
stars: 0
tags:
  - mlx
---

# GLM-4.7-Flash-6bit

> GLM-4.7-Flash-6bit - mlx-community 在 ModelScope 开源的模型。mlx-community/GLM-4.7-Flash-6bit

mlx-community/GLM-4.7-Flash-6bit 是 ModelScope 魔搭社区上的 811.0M 参数text-generation模型，采用 mit 许可，基于 zai-org/GLM-4.7-Flash 构建。

- **Repository**: mlx-community/GLM-4.7-Flash-6bit
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 811.0M
- **Base model**: zai-org/GLM-4.7-Flash
- **Tags**: mlx
- **Downloads**: 78
- **Stars**: 0
- **Last updated**: 2026-01-26

Source: https://www.modelscope.cn/models/mlx-community/GLM-4.7-Flash-6bit

---

# mlx-community/GLM-4.7-Flash-6bit

This model [mlx-community/GLM-4.7-Flash-6bit](https://huggingface.co/mlx-community/GLM-4.7-Flash-6bit) was
converted to MLX format from [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash)
using mlx-lm version **0.30.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.7-Flash-6bit")

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)
```