Qwen2.5-3B-Instruct-4bit

Name: Qwen2.5-3B-Instruct-4bit
Author: mlx-community

3B open-weight LLM by mlx-community

Live

Open / InstallLast updated August 5, 2026

Description

Qwen2.5-3B-Instruct-4bit is an open-weight text-generation model with roughly 3B parameters published by mlx-community on the Hugging Face Hub. It has 70,051 downloads. Runs with mlx.

Author

mlx-community

Platform

api

Pricing model

free

Capabilities

Text generation
Conversational
Library: mlx
3B parameters

Benchmarks

No benchmark results have been added yet.