This repository hosts a quantized FP8 version of the Qwen3 30B-A3B Thinking model. It is designed for complex reasoning tasks, multi-step tool use, and agentic workflows. The model can be used locally with Docker or via pip with the Transformers library.
Qwen3 30B A3B Thinking 2507 sits in PulseGate's Foundation models & chat category. It focuses on providing high-performance open reasoning models that can be self-hosted or used via API. Qwen3 30B A3B Thinking 2507 is an open-source project aimed at developers. The project is open source (Open Source). It runs on the web, the command line, and API, and it can be self-hosted.
Behind Qwen3 30B A3B Thinking 2507 is Qwen, and it first shipped in 2024. Development happens publicly on GitHub with 27.5k stars. It competes in a saturated segment with 25 similar apps in PulseGate's index. Among its 3 catalogued features are advanced reasoning, tool calling, and multi-step thinking.
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