lmsys/qwen-image-edit-modelopt-nvfp4-sglang

Qwen Image Edit ModelOpt NVFP4 for SGLang

This repository contains a full Hugging Face-style SGLang Diffusion checkpoint exported from Qwen/Qwen-Image-Edit with NVIDIA ModelOpt NVFP4 quantization support. The checkpoint can be loaded directly with --model-path in SGLang; no separate --transformer-path override is required.

Export provenance

The checkpoint was generated on an NVIDIA B200 machine by applying NVIDIA ModelOpt PR #1706 locally (qwen-image-svdquant-nvfp4-pr) and exporting a full pipeline directory for SGLang validation.

Export settings:

• Base model: Qwen/Qwen-Image-Edit
• Pipeline class: QwenImageEditPipeline
• Quantization recipe: SVDQuant NVFP4 / FP4 export through ModelOpt
• Main export flag: --format fp4
• Calibration: max calibration with 8 representative prompts
• Block size: 16
• Quantized scope: diffusion transformer blocks
• BF16 fallbacks: first two and last two transformer blocks, plus attention quantizers disabled during export
• Validation target: NVIDIA B200 / Blackwell using SGLang Diffusion

Validated as a full SGLang Diffusion image-edit checkpoint on B200.

SGLang usage

sglang generate \
  --model-path lmsys/qwen-image-edit-modelopt-nvfp4-sglang \
  --prompt "A tiny astronaut reading a book under a glass greenhouse" \
  --save-output

For edit pipelines, pass the normal SGLang Diffusion image-edit inputs in addition to --model-path lmsys/qwen-image-edit-modelopt-nvfp4-sglang.

Notes

This is a performance and integration validation checkpoint for SGLang Diffusion NVFP4 support. Please compare generated images with the corresponding BF16 base model for quality-sensitive use cases.