MaziyarPanahi maintains this repository of GGUF files for the Llama 3.2 3B Instruct model. The model offers a strong balance of capability and efficiency, supporting instruction following and multimodal (vision) features in its base form. It is designed for local deployment via popular open-source inference engines.
Llama 3.2 3B Instruct is a Foundation models & chat project. Efficiently running a 3-billion-parameter vision-capable instruction model on local hardware with multiple quantization choices. It is built as an open-source project for developers. Llama 3.2 3B Instruct is open source under the MIT license. It ships for the web, the command line, and API, and it can be self-hosted.
Behind Llama 3.2 3B Instruct is MaziyarPanahi, and it first shipped in 2023. The project is developed in the open on GitHub with 122.3k stars and 1.2k commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 17 similar projects. Among its 4 catalogued features are instruction following, GGUF quantization, and vision-ready base. It exposes integrations via a public API.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do