This repository hosts a GPTQ 4-bit quantized variant of the Gemma-3-27B-IT model with 128-group size. It is designed for efficient inference while preserving most of the original model quality. The model follows the Gemma chat template and is suitable for local deployment using compatible inference engines.
In the Foundation models & chat space, Gemma 3 27b It GPTQ 4b 128g takes a focused approach. It focuses on running the 27B Gemma 3 model on hardware with limited VRAM through 4-bit quantization. It is built as an open-source project for developers. Gemma 3 27b It GPTQ 4b 128g is open source under the Open Source license. It runs on the web, the command line, and API.
Behind Gemma 3 27b It GPTQ 4b 128g is ISTA-DASLab.
Latest indexed changes and source events
ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g verified by the PulseGate indexer
Other apps tracked under the same category.
