README.md

---
library_name: mlx
tags:
- prime-rl
- verifiers
- prime-intellect
- reinforcement-learning
- reasoning
- agentic
- mixture-of-experts
- mlx
license: mit
language:
- en
base_model: PrimeIntellect/INTELLECT-3
pipeline_tag: text-generation
---

# mlx-community/INTELLECT-3-8bit

This model [mlx-community/INTELLECT-3-8bit](https://huggingface.co/mlx-community/INTELLECT-3-8bit) was
converted to MLX format from [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3)
using mlx-lm version **0.28.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/INTELLECT-3-8bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```