---
license: apache-2.0
language:
- en
base_model: janhq/Jan-code-4b
pipeline_tag: text-generation
library_name: mlx
tags:
- agent
- mlx
---

# MercuriusDream/Jan-code-4b-MLX-nvfp4

This model [MercuriusDream/Jan-code-4b-MLX-nvfp4](https://huggingface.co/MercuriusDream/Jan-code-4b-MLX-nvfp4) was
converted to MLX format from [janhq/Jan-code-4b](https://huggingface.co/janhq/Jan-code-4b)
using mlx-lm version **0.30.7**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("MercuriusDream/Jan-code-4b-MLX-nvfp4")

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)
```