Gemma 4 31B IT QAT NVFP4 Blackwell This repository contains the Gemma 4 31B Instruction Tuned model quantized to native FP4 (NVFP4) precision for high efficiency inference on NVIDIA Blackwell GPU architectures (e.g., B200, B100). Quantized from the official unquantized QAT weights ( google/gemma 4 31B it qat q4 0 unquantized ) using NVIDIA Model Optimizer ( modelopt ) , this model delivers exceptional throughput and memory savings while preserving high quality by leveraging the Quantization Aware Training (QAT) properties of the base checkpoint. Model Details Base Model: google/gemma 4 31B it qat q4 0 unquantized Quantization Format: NVFP4 (native FP4 on Blackwell) Group Size: 16 (per group scaling) Excluded Modules: lm head , model.embed vision , model.vision tower (runs in high precision) Producer: NVIDIA Model Optimizer ( modelopt ) [!NOTE] Why does Hugging Face show "17B params" instead of "31B"? Hugging Face calculates the parameter count dynamically from the tensor shapes in the safetensors files. Because this model's weights are quantized to native 4 bit (FP4) and packed (two 4 bit weights per single int8 byte), the physical tensor dimensions are halved (e.g., a shape of [53…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy