---
license: apache-2.0
base_model: mlx-community/Qwen3-4B-Instruct-2507-4bit
tags:
- mlx
- qwen3
- tool-calling
- agent
- macos
- applescript
- voice-assistant
- on-device
language:
- en
pipeline_tag: text-generation
library_name: mlx
---

# FahrenheitResearch/FR-Argus-4B

This model [FahrenheitResearch/FR-Argus-4B](https://huggingface.co/FahrenheitResearch/FR-Argus-4B) was
converted to MLX format from [mlx-community/Qwen3-4B-Instruct-2507-4bit](https://huggingface.co/mlx-community/Qwen3-4B-Instruct-2507-4bit)
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("FahrenheitResearch/FR-Argus-4B")

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)
```