This is an NVFP4 quantized version of the Gemma 4 12B instruction-tuned (it) model, published by RedHatAI. It includes an advanced chat template with tool-calling support and is designed for efficient inference on NVIDIA hardware. The model is hosted on Hugging Face for use in local or enterprise AI deployments.
Gemma 4 12B It sits in PulseGate's Foundation models & chat category. It focuses on running large instruction-tuned models efficiently on NVIDIA GPUs using optimized quantization formats. It is built as an open-source project for developers. Gemma 4 12B It is open source under the Apache-2.0 license. The product ships for the web and API.
RedHatAI builds and maintains Gemma 4 12B It, and the product first shipped in 2019. Development happens publicly on GitHub with 3.6k stars and 161 commits in the last 90 days. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include Instruction Tuning, Quantized Weights, and Tool Calling.
Latest indexed changes and source events
RedHatAI/gemma-4-12B-it-NVFP4 verified by the PulseGate indexer