---
title: gpt-oss-120b-GGUF
canonical_url: "https://www.modelscope.cn/models/ggml-org/gpt-oss-120b-GGUF"
md_url: "https://www.modelscope.cn/models/ggml-org/gpt-oss-120b-GGUF.md"
repository: ggml-org/gpt-oss-120b-GGUF
last_updated: 2026-10-19
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - openai/gpt-oss-120b
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 18584
stars: 3
tags:
  - gguf
  - quantized
---

# gpt-oss-120b-GGUF

> gpt-oss-120b-GGUF - ggml-org 在 ModelScope 开源的模型。Run it in the Llama app: https://llama.app

ggml-org/gpt-oss-120b-GGUF 是 ModelScope 魔搭社区上的text-generation模型，采用 apache-2.0 许可，基于 openai/gpt-oss-120b 构建。

- **Repository**: ggml-org/gpt-oss-120b-GGUF
- **License**: apache-2.0
- **Tasks**: text-generation
- **Base model**: openai/gpt-oss-120b
- **Tags**: gguf, quantized
- **Downloads**: 18584
- **Stars**: 3
- **Last updated**: 2026-10-19

Source: https://www.modelscope.cn/models/ggml-org/gpt-oss-120b-GGUF

---

# gpt-oss-120b

Run it in the Llama app: https://llama.app

Or from the terminal:

```bash
llama serve -hf ggml-org/gpt-oss-120b-GGUF
```

### Source models
- https://huggingface.co/openai/gpt-oss-120b
- https://huggingface.co/nvidia/gpt-oss-120b-Eagle3-v3

### TODOs

- add info

> [!IMPORTANT]
> This model is automatically converted using https://github.com/ggml-org/convert