Safetensors NVFP4

Community build

A quantized build of the model Qwen-Image-2.1.

Publisher
MesmerTech
Source platform
HUGGINGFACE
Quantization
NVFP4
Revision
868fc8b147de20f2c6e6835b694b2c4d9de9b5a6
Updated
2026-09-26
Total size
4.54 GB

File list

Paths and sizes come from the release page; a missing size shows "not provided".

File pathSize
qwen-image-2.1-fp4-r128.safetensors4.54 GB

Linked benchmarks

Only benchmarks tied to this exact release are listed.

HardwareFrameworkQuantGen timeVRAM usedSamplesEvidence
NVIDIA RTX 5090NunchakuNVFP4 rank-1284.8 s18.74 GB1L0 Self-reported

Deployment guidance

This site doesn't guess whether or how this build runs on your machine. General local-deployment tutorials are linked below; if a link or data on this page is wrong, please tell us.