---
base_model: BruhzWater/Sapphira-L3.3-70b-0.1
library_name: transformers
tags:
- mergekit
- merge
- mlx
- mlx-my-repo
---

# mrtoots/BruhzWater-Sapphira-L3.3-70b-0.1-mlx-8Bit

The Model [mrtoots/BruhzWater-Sapphira-L3.3-70b-0.1-mlx-8Bit](https://huggingface.co/mrtoots/BruhzWater-Sapphira-L3.3-70b-0.1-mlx-8Bit) was converted to MLX format from [BruhzWater/Sapphira-L3.3-70b-0.1](https://huggingface.co/BruhzWater/Sapphira-L3.3-70b-0.1) using mlx-lm version **0.26.4**.



## Toots' Note:

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

Settings and how best to run found on the [original model page](https://huggingface.co/BruhzWater/Sapphira-L3.3-70b-0.1).

🦛 <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/Sapphira-L3.3-70b-0.1-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)
```