Qwen2.5-Coder-14B-Instruct-MLX-4bit

Name: Qwen2.5-Coder-14B-Instruct-MLX-4bit
Author: lmstudio-community

14B open-weight LLM by lmstudio-community

Live

Open / InstallLast updated August 5, 2026

Description

Qwen2.5-Coder-14B-Instruct-MLX-4bit is an open-weight text-generation model with roughly 14B parameters published by lmstudio-community on the Hugging Face Hub. It has 129,852 downloads. Runs with mlx.

Author

lmstudio-community

Platform

api

Pricing model

free

Capabilities

Text generation
Conversational
Library: mlx
14B parameters

Benchmarks

No benchmark results have been added yet.