---
license: apache-2.0
language:
- hu
- en
- zh
tags:
- puli
- mlx
- mlx-my-repo
base_model: NYTK/PULI-Trio-Q
---

# berszi/PULI-Trio-Q-mlx-4Bit

The Model [berszi/PULI-Trio-Q-mlx-4Bit](https://huggingface.co/berszi/PULI-Trio-Q-mlx-4Bit) was converted to MLX format from [NYTK/PULI-Trio-Q](https://huggingface.co/NYTK/PULI-Trio-Q) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("berszi/PULI-Trio-Q-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)
```