---
license: apache-2.0
datasets:
- HuggingFaceFW/fineweb-edu
- SupraLabs/SupraThink-Dataset-500x
language:
- en
pipeline_tag: text-generation
library_name: transformers
tags:
- supra
- chimera
- 50m
- llama
- small
- open
- open-source
- cpu
- tiny
- slm
- reasoning
- think
- thinking
- mlx
- mlx-my-repo
base_model: SupraLabs/Supra-50M-Reasoning
---

# usermma/Supra-50M-Reasoning-mlx-5Bit

The Model [usermma/Supra-50M-Reasoning-mlx-5Bit](https://huggingface.co/usermma/Supra-50M-Reasoning-mlx-5Bit) was converted to MLX format from [SupraLabs/Supra-50M-Reasoning](https://huggingface.co/SupraLabs/Supra-50M-Reasoning) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("usermma/Supra-50M-Reasoning-mlx-5Bit")

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)
```