Qwen3-235B-A22B-FP8 is a very large Mixture-of-Experts language model from Alibaba's Qwen team. With 235 billion total parameters and 22 billion activated per token, it supports advanced tool calling, multi-step reasoning, and complex instruction following. The FP8 version enables more efficient inference for this frontier-scale model.
Qwen3 235B A22B sits in PulseGate's Foundation models & chat category. It focuses on scaling language model capabilities to frontier levels while maintaining computational efficiency through sparse activation. Qwen3 235B A22B is an open-source project aimed at organizations and researchers needing maximum model scale. The project is open source (Open Source). It runs on the web, the command line, and API.
Behind Qwen3 235B A22B is Qwen, based in China, and it first shipped in 2024. The project is developed in the open on GitHub with 27.4k stars. It operates in a well-populated space: PulseGate tracks 7 similar projects. Key capabilities include mixture of Experts, Tool Calling, and Advanced Reasoning.
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