README.md

---
library_name: mlx
license: apache-2.0
language:
- en
- fr
- es
- it
- pt
- zh
- ar
- ru
tags:
- mlx
base_model: HuggingFaceTB/SmolLM3-3B
pipeline_tag: text-generation
---

# arthurcollet/SmolLM3-3B-mlx

This model [arthurcollet/SmolLM3-3B-mlx](https://huggingface.co/arthurcollet/SmolLM3-3B-mlx) was
converted to MLX format from [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B)
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("arthurcollet/SmolLM3-3B-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)
```