Qwen2.5-7B-Instruct-bnb-4bit is a quantized variant of Alibaba's Qwen2.5 7B Instruct model, provided by Unsloth. It uses bitsandbytes 4-bit quantization to enable efficient inference while maintaining strong performance on instruction following and tool use. The model is available on Hugging Face for developers building local or cloud LLM applications.
Qwen2.5 7B Instruct Bnb is a Foundation models & chat product. It focuses on running a capable 7B instruct LLM efficiently on consumer hardware with reduced memory requirements. It is built as an open-source project for developers. Qwen2.5 7B Instruct Bnb is open source under the Apache-2.0 license. The product ships for the web, the command line, and API.
Unsloth builds and maintains Qwen2.5 7B Instruct Bnb, 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 4-bit quantized, instruct model, and tool calling support.
Latest indexed changes and source events
unsloth/Qwen2.5-7B-Instruct-bnb-4bit verified by the PulseGate indexer
