This is a 4-bit quantized version of Meta's Llama 3.2 3B Instruct model, optimized by Unsloth for faster inference and lower memory usage. It maintains strong instruction-following capabilities while being suitable for deployment on laptops and modest GPUs. The model includes full chat templates and is compatible with the Hugging Face ecosystem.
In the Foundation models & chat space, Llama 3.2 3B Instruct Bnb takes a focused approach. It focuses on running powerful 3B parameter language models efficiently on consumer hardware with minimal memory requirements. It is built as an open-source project for developers. Llama 3.2 3B Instruct Bnb is open source under the Apache-2.0 license. Llama 3.2 3B Instruct Bnb is available on the web, the command line, and API.
It is developed by Unsloth, and the product first shipped in 2023. Development happens publicly on GitHub with 68.7k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 17 similar tools. Key capabilities include Quantized LLM, Instruction Tuning, and 4-bit Precision.
Latest indexed changes and source events
unsloth/Llama-3.2-3B-Instruct-bnb-4bit verified by the PulseGate indexer
