---
language:
- en
library_name: transformers
tags:
- glm
- glm4
- MOE
- pruning
- compression
- reap
- cerebras
- code
- function-calling
- agentic
- mlx
- mlx-my-repo
license: apache-2.0
pipeline_tag: text-generation
base_model: 0xSero/GLM-4.7-REAP-40
---

# thejson/GLM-4.7-REAP-40-mlx-4Bit

The Model [thejson/GLM-4.7-REAP-40-mlx-4Bit](https://huggingface.co/thejson/GLM-4.7-REAP-40-mlx-4Bit) was converted to MLX format from [0xSero/GLM-4.7-REAP-40](https://huggingface.co/0xSero/GLM-4.7-REAP-40) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("thejson/GLM-4.7-REAP-40-mlx-4Bit")

prompt="hello"

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

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