This is an INT4 quantized version of the Gemma-4 31B instruction-tuned model created by Intel using the AutoRound quantization technique. It is hosted on Hugging Face and designed for efficient local or server-based inference while maintaining strong performance. The model supports standard chat templates and is suitable for a wide range of text generation tasks.
Gemma 4 31B It Int4 AutoRound sits in PulseGate's Foundation models & chat category. It focuses on running large 31B parameter language models efficiently on consumer or edge hardware through quantization. Gemma 4 31B It Int4 AutoRound is an open-source project aimed at AI developers and researchers. The project is open source (Apache-2.0). Gemma 4 31B It Int4 AutoRound is available on the web and API.
It is developed by Intel (United States), and it first shipped in 2024. Development happens publicly on GitHub with 1.5k stars and 173 commits in the last 90 days. Among its 4 catalogued features are Instruction Tuned, INT4 Quantization, and AutoRound Optimization.
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