AI가 움직이고 미래가 업데이트됩니다.Gemma-4-26B-A4B-it-NVFP4A16
**First community NVFP4 quantization** of google/gemma-4-26B-A4B-it — the Mixture-of-Experts variant of Gemma 4 with 25.2B total parameters and only 3.8B active per token. Tested on NVIDIA DGX Spark (128GB unified memory, GB10 Blackwell, SM 12.1). Model loads at 15.7 GiB — plenty of headroom for 65K+ context with FP8 KV cache. Gemma 4 MoE stores expert weights as **fused 3D tensors** (`nn.Parameter` of shape `[128, dim, dim]`) instead of individual `nn.Linear` modules. NVIDIA Model Optimizer (modelopt) only quantizes `nn.Linear` — it silently skips the 3D expert parameters, which are 91% of the model.
번역 준비 중입니다. 원문을 표시합니다.
**First community NVFP4 quantization** of google/gemma-4-26B-A4B-it — the Mixture-of-Experts variant of Gemma 4 with 25.2B total parameters and only 3.8B active per token. Tested on NVIDIA DGX Spark (128GB unified memory, GB10 Blackwell, SM 12.1). Model loads at 15.7 GiB — plenty of headroom for 65K+ context with FP8 KV cache. Gemma 4 MoE stores expert weights as **fused 3D tensors** (`nn.Parameter` of shape `[128, dim, dim]`) instead of individual `nn.Linear` modules. NVIDIA Model Optimizer (modelopt) only quantizes `nn.Linear` — it silently skips the 3D expert parameters, which are 91% of the model.