Qwen3-30B-A3B-FP8 is an FP8 quantized version of Alibaba's Qwen3 series Mixture-of-Experts model. It offers strong performance on reasoning and tool-use tasks while significantly reducing memory requirements compared to full-precision versions. The model supports advanced features such as function calling and multi-step tool use and is distributed for use with Transformers and compatible inference engines.
Qwen3 30B A3B sits in PulseGate's Tool calling category. Efficiently running a large-scale 30B+ parameter Mixture-of-Experts language model with reduced precision for lower memory and faster inference. It is built as an open-source project for AI developers and enterprises. The project is open source (Open Source). It runs on the web, the command line, and API.
Behind Qwen3 30B A3B is Qwen, and it first shipped in 2024. Development happens publicly on GitHub with 27.4k stars. The category is crowded — PulseGate's index counts 25 comparable projects. Key capabilities include mixture of Experts, Tool Calling, and Quantized Weights.
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