This is a community-quantized (NVFP4) version of Google's Gemma 4 31B instruction-tuned (it) model hosted on Hugging Face. It enables efficient local or hosted inference of a powerful open LLM using libraries such as Transformers or vLLM. The model includes a chat template and tokenizer configuration optimized for conversational use.
Gemma 4 31B It NVFP4 Turbo is a Foundation models & chat product. It focuses on running large language models efficiently on consumer or edge hardware without high compute costs. It is built as an open-source project for developers. Gemma 4 31B It NVFP4 Turbo is open source under the Open Source license. It runs on the web, the command line, and API.
LilaRest builds and maintains Gemma 4 31B It NVFP4 Turbo, and the product first shipped in 2025. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include quantized weights, instruction tuned, and chat template.
Latest indexed changes and source events
LilaRest/gemma-4-31B-it-NVFP4-turbo verified by the PulseGate indexer
Other apps tracked under the same category.
