Qwen3-32B-bnb-4bit is a bitsandbytes 4-bit quantized version of the Qwen3-32B model, optimized for use with the Unsloth library. It supports advanced features such as tool calling and is designed for efficient fine-tuning and inference on GPUs with limited VRAM.
Qwen3 32B Bnb is a Foundation models & chat product. It focuses on running the large 32B Qwen3 model with reduced memory requirements using 4-bit quantization. It is built as an open-source project for AI developers and researchers. Qwen3 32B Bnb is open source under the Open Source license. It runs on the web, the command line, and API.
It is developed by unsloth, 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 14 similar tools. Key capabilities include 4-bit Quantization, Unsloth Optimized, and Tool Calling.
Latest indexed changes and source events
unsloth/Qwen3-32B-bnb-4bit verified by the PulseGate indexer
