---
title: gpt-oss-20b-MLX-4bit
canonical_url: "https://www.modelscope.ai/models/NexaAI/gpt-oss-20b-MLX-4bit"
md_url: "https://www.modelscope.ai/models/NexaAI/gpt-oss-20b-MLX-4bit.md"
repository: NexaAI/gpt-oss-20b-MLX-4bit
last_updated: 2025-11-25
license: apache-2.0
model_type:
  - gpt_oss
architectures:
  - GptOssForCausalLM
base_model:
  - openai/gpt-oss-20b
base_model_relation: quantized
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 127
stars: 0
tags:
  - mlx
  - gpt
  - openai
  - chatGPT
---

# gpt-oss-20b-MLX-4bit

> gpt-oss-20b-MLX-4bit - An open-source model by NexaAI on ModelScope. NexaAI/gpt-oss-20b-MLX-4bit

NexaAI/gpt-oss-20b-MLX-4bit is a machine learning model on ModelScope. licensed under apache-2.0. derived from openai/gpt-oss-20b.

- **Repository**: NexaAI/gpt-oss-20b-MLX-4bit
- **License**: apache-2.0
- **Base model**: openai/gpt-oss-20b
- **Tags**: mlx, gpt, openai, chatGPT
- **Downloads**: 127
- **Stars**: 0
- **Last updated**: 2025-11-25

Source: https://www.modelscope.ai/models/NexaAI/gpt-oss-20b-MLX-4bit

---

# NexaAI/gpt-oss-20b-MLX-4bit

## Quickstart

Run them directly with [nexa-sdk](https://github.com/NexaAI/nexa-sdk) installed
In nexa-sdk CLI:

```bash
NexaAI/gpt-oss-20b-MLX-4bit
```

## Overview
This is a 4-bit quantized version of the OpenAI GPT OSS 20B model, optimized for Apple Silicon using the MLX framework. The model was successfully converted from the original `gpt_oss` architecture to MLX format using the development version of `mlx-lm`.


## Reference
**Original model card**: [InferenceIllusionist/gpt-oss-20b-MLX-4bit](https://huggingface.co/InferenceIllusionist/gpt-oss-20b-MLX-4bit)