---
title: INTELLECT-3-8bit-gs32
canonical_url: "https://www.modelscope.cn/models/mlx-community/INTELLECT-3-8bit-gs32"
md_url: "https://www.modelscope.cn/models/mlx-community/INTELLECT-3-8bit-gs32.md"
repository: mlx-community/INTELLECT-3-8bit-gs32
last_updated: 2025-11-27
license: "Apache License 2.0"
inference_backends:
  - "deploy_task text"
  - "sglang 0.5.2"
downloads: 23
stars: 0
---

# INTELLECT-3-8bit-gs32

> INTELLECT-3-8bit-gs32 - mlx-community 在 ModelScope 开源的模型。mlx-community/INTELLECT-3-8bit-gs32

mlx-community/INTELLECT-3-8bit-gs32 是 ModelScope 魔搭社区上的机器学习模型，采用 Apache License 2.0 许可，可用 deploy_task text、sglang 0.5.2 部署。

- **Repository**: mlx-community/INTELLECT-3-8bit-gs32
- **License**: Apache License 2.0
- **Inference backends**: deploy_task text, sglang 0.5.2
- **Downloads**: 23
- **Stars**: 0
- **Last updated**: 2025-11-27

Source: https://www.modelscope.cn/models/mlx-community/INTELLECT-3-8bit-gs32

---

# mlx-community/INTELLECT-3-8bit-gs32

This model [mlx-community/mlx-community/INTELLECT-3-8bit-gs32](https://huggingface.co/mlx-community/INTELLECT-3-8bit-gs32) was converted to MLX format from [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3)
using mlx-lm version **0.28.3**.

## Recipe:
* 8-bit
* group-size 32
* 9 bits per weight (bpw)

You can find more similar MLX model quants for an Apple Mac Studio at https://huggingface.co/bibproj

Enjoy!

---

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/INTELLECT-3-8bit-gs32")

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)
```