Qwen3-235B-A22B is a 235 billion parameter Mixture-of-Experts model with 22 billion active parameters, provided in FP8 precision. It is an instruction-tuned model supporting advanced features such as tool calling. The model represents the latest generation of the Qwen series and is available for local and hosted inference.
Qwen3 235B A22B Instruct 2507 sits in PulseGate's Foundation models & chat category. It focuses on delivering frontier-level language model performance through a massive MoE architecture while controlling inference costs with FP8 quantization. It is built as an open-source project for developers. Qwen3 235B A22B Instruct 2507 is open source under the Open Source license. The product ships for the web, the command line, and API.
It is developed by Qwen, and the product first shipped in 2024. Development happens publicly on GitHub with 27.4k stars. It operates in a well-populated space: PulseGate tracks 7 similar tools. Key capabilities include text generation, mixture of experts, and tool calling.
Latest indexed changes and source events
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
