This is a 4-bit AWQ quantized version of a Ministral 3B reasoning model. It is designed for efficient local inference while maintaining strong reasoning capabilities. The model uses compressed-tensors quantization and is available on Hugging Face for use with Transformers or inference engines that support GGUF/AWQ formats.
Ministral 3 8B Reasoning 2512 is a Foundation models & chat project. It focuses on running a capable reasoning model efficiently on consumer hardware with reduced memory requirements. Ministral 3 8B Reasoning 2512 is an open-source project aimed at developers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Behind Ministral 3 8B Reasoning 2512 is cyankiwi, and it first shipped in 2019. The project is developed in the open on GitHub with 3.6k stars and 159 commits in the last 90 days. Among its 4 catalogued features are reasoning model, 4-bit quantization, and AWQ quantization.
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