This is a GGUF-quantized release of Qwen3-235B-A22B, a massive mixture-of-experts language model optimized for local execution. It supports advanced reasoning, tool calling, and follows a specific chat template. Provided by Unsloth, it enables efficient inference of one of the largest open models using tools like llama.cpp.
Qwen3 235B A22B sits in PulseGate's Foundation models & chat category. It focuses on running extremely large 235B-parameter models efficiently on consumer or enterprise hardware using quantized formats. It is built as an open-source project for developers and researchers needing local LLMs. Qwen3 235B A22B is open source under the Apache-2.0 license. It runs on the web and the command line.
Behind Qwen3 235B A22B is Unsloth, and the product first shipped in 2023. Development happens publicly on GitHub with 68.4k stars and 1.2k commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include Large Language Model, Tool Calling, and Quantized GGUF.
Latest indexed changes and source events
unsloth/Qwen3-235B-A22B-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
