Nvidia Nemotron 3.5 Lightning Runs Locally on a Single GPU
… The NVFP4 repository is approximately 21.6GB before runtime overhead and context-cache allocation are considered. …
Tracked topic
… The NVFP4 repository is approximately 21.6GB before runtime overhead and context-cache allocation are considered. …
… At sparse NVFP4 precision, the processor is capable of delivering up to 50 PFLOPS of AI compute performance. …