This is an AWQ 4-bit quantized version of the Qwen3-30B-A3B-Thinking model. It includes support for tool calling and specialized thinking capabilities. The model is distributed on Hugging Face and is intended for local inference using libraries such as Transformers or vLLM.
Qwen3 30B A3B Thinking 2507 sits in PulseGate's Tool calling category. It focuses on running large language models efficiently on consumer hardware with reduced memory requirements. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web, the command line, and API.
cyankiwi builds and maintains Qwen3 30B A3B Thinking 2507, and it first shipped in 2024. Development happens publicly on GitHub with 27.4k stars. PulseGate's similarity index places it among 19 comparable projects. Among its 3 catalogued features are Quantized Model, Tool Calling, and Thinking Mode.
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