---
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- chat
- instruct
- small-model
- 135m
- quark
- mlx
base_model: ThingAI/Quark-135m
---

# usermma/Quark-135m-mlx-5bit

The Model [usermma/Quark-135m-mlx-5bit](https://huggingface.co/usermma/Quark-135m-mlx-5bit) was converted to MLX format from [ThingAI/Quark-135m](https://huggingface.co/ThingAI/Quark-135m) using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("usermma/Quark-135m-mlx-5bit")

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)
```