---
base_model: sophosympatheia/Nova-Tempus-70B-v0.3
library_name: transformers
tags:
- mergekit
- merge
- not-for-all-audiences
- mlx
- mlx-my-repo
license: llama3.3
language:
- en
---

# beezu/Nova-Tempus-70B-v0.3-MLX-4Bit

The Model [beezu/Nova-Tempus-70B-v0.3-MLX-4Bit](https://huggingface.co/beezu/Nova-Tempus-70B-v0.3-Q4-mlx) was converted to MLX format from [sophosympatheia/Nova-Tempus-70B-v0.3](https://huggingface.co/sophosympatheia/Nova-Tempus-70B-v0.3) using mlx-lm version **0.20.5**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("beezu/Nova-Tempus-70B-v0.3-Q4-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)
```