---
title: gpt-oss-120b-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/gpt-oss-120b-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/gpt-oss-120b-4bit.md"
repository: mlx-community/gpt-oss-120b-4bit
last_updated: 2025-08-06
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - gpt_oss
architectures:
  - GptOssForCausalLM
parameters: 18.3B
tensor_type:
  - BF16
  - U32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text"
  - "sglang 0.5.2"
downloads: 206
stars: 0
tags:
  - vllm
---

# gpt-oss-120b-4bit

> gpt-oss-120b-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/gpt-oss-120b-4bit

mlx-community/gpt-oss-120b-4bit 是 ModelScope 魔搭社区上的 18.3B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text、sglang 0.5.2 部署。

- **Repository**: mlx-community/gpt-oss-120b-4bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 18.3B
- **Inference backends**: deploy_task text, sglang 0.5.2
- **Tags**: vllm
- **Downloads**: 206
- **Stars**: 0
- **Last updated**: 2025-08-06

Source: https://www.modelscope.cn/models/mlx-community/gpt-oss-120b-4bit

---

# mlx-community/gpt-oss-120b-4bit

This model [mlx-community/gpt-oss-120b-4bit](https://huggingface.co/mlx-community/gpt-oss-120b-4bit) was
converted to MLX format from [None](https://huggingface.co/None)
using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/gpt-oss-120b-4bit")

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)
```