---
library_name: transformers
license: apache-2.0
base_model: allura-org/remnant-glm4-32b
tags:
- roleplay
- conversational
- axolotl
- mlx
- mlx-my-repo
---

# Wwayu/remnant-glm4-32b-mlx-6Bit

The Model [Wwayu/remnant-glm4-32b-mlx-6Bit](https://huggingface.co/Wwayu/remnant-glm4-32b-mlx-6Bit) was converted to MLX format from [allura-org/remnant-glm4-32b](https://huggingface.co/allura-org/remnant-glm4-32b) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Wwayu/remnant-glm4-32b-mlx-6Bit")

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)
```