filipe(@filicroval):legendary drop from NVIDIA: ModelOpt 0.45.0 biggest additions: - New NVFP4 (W4A16) weight-only quantization format that requires no calibration - Better MoE support (including mixed NVFP4 + FP8 recipes for models like Nemotron) - Easy MXFP4 → NVFP4 conversion for models like DeepSeek V4 and GPT-OSS - Various improvements for large-scale PTQ and Megatron workflows looks like NVIDIA is pushing harder on making 4-bit inference more practical and calibration-free.

filipe

@filicroval

data eng | 1xAsus Ascent GX10 | benchmarking local models so you don't have to

参加 May 2023

214 フォロー中 153.4K ファン

filipe@filicroval

2026.07.06 14:48

legendary drop from NVIDIA: ModelOpt 0.45.0 biggest additions: - New NVFP4 (W4A16) weight-only quantization format that requires no calibration - Better MoE support (including mixed NVFP4 + FP8 recipes for models like Nemotron) - Easy MXFP4 → NVFP4 conversion for models like DeepSeek V4 and GPT-OSS - Various improvements for large-scale PTQ and Megatron workflows looks like NVIDIA is pushing harder on making 4-bit inference more practical and calibration-free.