A quantized variant of the Qwen3-Coder model using AWQ 4-bit compression. It is designed for local inference of code generation and programming assistance tasks while significantly lowering VRAM usage compared to the original model. The model includes a chat template suitable for instruction following and tool use.
Qwen3 Coder 30B A3B Instruct is a Coding AI & assistants project. It focuses on running large coding-focused language models with reduced memory requirements on consumer hardware. Qwen3 Coder 30B A3B Instruct is an open-source project aimed at developers. Qwen3 Coder 30B A3B Instruct is open source under the Open Source license. It ships for the web, the command line, and API.
It is developed by cyankiwi, and it first shipped in 2024. Development happens publicly on GitHub with 16.7k stars. It operates in a well-populated space: PulseGate tracks 18 similar projects. Among its 3 catalogued features are quantized weights, code generation, and instruct-tuned.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do