Software Development

ModelOpt Post-Training Quantization

Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AWQ", "quantize LLM", "quantize MoE", "quantize VLM", or needs to produce a quantized HuggingFace checkpoint from a pretrained model using ModelOpt. Do NOT use for multi-candidate recipe exploration or optimization (use quant-recipe-search).

Publisher / source

NVIDIA/Model-Optimizer (found on GitHub top repositories)

Upstream record

NVIDIA/Model-Optimizer

Version

Version 1

Published

2026-11-05

Publication review

Approved for publication

Content fingerprint

823c7c9c307d4be8f6725e305144b109feee1de34b1c5f06ff0ec9ee4d064aff