---
title: GLM-4.7-REAP-50-mixed-3-4-bits
canonical_url: "https://www.modelscope.cn/models/mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits"
md_url: "https://www.modelscope.cn/models/mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits.md"
repository: mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits
last_updated: 2026-01-04
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - glm4_moe
architectures:
  - Glm4MoeForCausalLM
base_model:
  - 0xSero/GLM-4.7-REAP-50
base_model_relation: quantized
parameters: 16.4B
tensor_type:
  - BF16
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text"
  - "sglang 0.5.2"
downloads: 43
stars: 0
tags:
  - glm
  - glm4
  - MOE
  - pruning
  - compression
  - reap
  - cerebras
  - code
  - function-calling
  - agentic
  - mlx
---

# GLM-4.7-REAP-50-mixed-3-4-bits

> GLM-4.7-REAP-50-mixed-3-4-bits - mlx-community 在 ModelScope 开源的模型。mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits

mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits 是 ModelScope 魔搭社区上的 16.4B 参数text-generation模型，采用 apache-2.0 许可，基于 0xSero/GLM-4.7-REAP-50 构建，可用 deploy_task text、sglang 0.5.2 部署。

- **Repository**: mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 16.4B
- **Base model**: 0xSero/GLM-4.7-REAP-50
- **Inference backends**: deploy_task text, sglang 0.5.2
- **Tags**: glm, glm4, MOE, pruning, compression, reap, cerebras, code, function-calling, agentic, mlx
- **Downloads**: 43
- **Stars**: 0
- **Last updated**: 2026-01-04

Source: https://www.modelscope.cn/models/mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits

---

# mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits

This model [mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits](https://huggingface.co/mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits) was
converted to MLX format from [0xSero/GLM-4.7-REAP-50](https://huggingface.co/0xSero/GLM-4.7-REAP-50)
using mlx-lm version **0.30.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/GLM-4.7-REAP-50-mixed-3-4-bits")

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)
```