---
license: other
license_name: katanemo-research
license_link: https://huggingface.co/katanemo/Arch-Agent-3B/blob/main/LICENSE
base_model: katanemo/Arch-Agent-3B
language:
- en
pipeline_tag: text-generation
library_name: mlx
tags:
- mlx
---

# Arch-Agent-3B-128k-q8-mlx

This model [Arch-Agent-3B-128k-q8-mlx](https://huggingface.co/Arch-Agent-3B-128k-q8-mlx) was
converted to MLX format from [katanemo/Arch-Agent-3B](https://huggingface.co/katanemo/Arch-Agent-3B)
using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Arch-Agent-3B-128k-q8-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```