README.md

---
base_model: Sao10K/L3-8B-Stheno-v3.2
datasets:
- Gryphe/Opus-WritingPrompts
- Sao10K/Claude-3-Opus-Instruct-15K
- Sao10K/Short-Storygen-v2
- Sao10K/c2-Logs-Filtered
language:
- en
license: cc-by-nc-4.0
tags:
- mlx
---

# L3-8B-Stheno-v3.2-MLX

This is the MLX version of the fantastic [L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) by Sao10K. Achieves roughly 10-15 tok/sec faster on my system then the original 4 bit quant.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("synk/L3-8B-Stheno-v3.2-MLX")

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)
```