---
license: apache-2.0
datasets:
- PrimeIntellect/Intellect-2-RL-Dataset
tags:
- mlx
base_model: PrimeIntellect/INTELLECT-2
---

# alexander583/INTELLECT-2-mlx-4Bit

The Model [alexander583/INTELLECT-2-mlx-4Bit](https://huggingface.co/alexander583/INTELLECT-2-mlx-4Bit) was converted to MLX format from [PrimeIntellect/INTELLECT-2](https://huggingface.co/PrimeIntellect/INTELLECT-2) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("alexander583/INTELLECT-2-mlx-4Bit")

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)
```