README.md

---
base_model: unsloth/Magistral-Small-2509
language:
- en
- fr
- de
- es
- pt
- it
- ja
- ko
- ru
- zh
- ar
- fa
- id
- ms
- ne
- pl
- ro
- sr
- sv
- tr
- uk
- vi
- hi
- bn
library_name: vllm
license: apache-2.0
inference: false
extra_gated_description: If you want to learn more about how we process your personal
  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
tags:
- vllm
- mistral-common
- mlx
- mlx-my-repo
---

# mrtoots/unsloth-Magistral-Small-2509-mlx-8Bit

The Model [mrtoots/unsloth-Magistral-Small-2509-mlx-8Bit](https://huggingface.co/mrtoots/unsloth-Magistral-Small-2509-mlx-8Bit) was converted to MLX format from [unsloth/Magistral-Small-2509](https://huggingface.co/unsloth/Magistral-Small-2509) using mlx-lm version **0.26.4**.




## Toots' Note:
This model was converted and quantized utilizing unsloth's version of Mistral's magistral-small-2509.

Please follow and support [mistral's work](https://huggingface.co/mistralai) and support [unsloth's work](https://huggingface.co/unsloth) if you like it!

🦛 <span style="color:#800080">If you want a free consulting session, </span>[fill out this form](https://forms.gle/xM9gw1urhypC4bWS6) <span style="color:#800080">to get in touch!</span> 🤗




## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mrtoots/Magistral-Small-2509-mlx-8Bit")

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)
```