NVIDIA 用 Model Optimizer 的 QAD 打造 Nemotron 3.5 Lightning NVFP4
Developing Nemotron 3.5 Lightning NVFP4 with QAD Using NVIDIA Model Optimizer
NVIDIA 发布 Nemotron 3.5 Lightning NVFP4 检查点，借助 NVIDIA Model Optimizer 的 QAD 方法在保持精度的同时实现最高 4 倍吞吐提升。该检查点体积从全精度版本的 66 GB 压缩至 22 GB。
Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models, developers can find...
Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models, developers can find the right-sized model for their needs. The new Nemotron 3.5 Lightning NVFP4 checkpoint, for example, preserves accuracy while unlocking up to 4x faster throughput. It’s compressed down to 22 GB from the 66 GB full precision checkpoint…
来源：NVIDIA Developer Blog · developer.nvidia.com