multimodalart's picture
multimodalart HF Staff
Initial NVFP4 demo for Cosmos3-Super-Text2Image
046dae3 verified
---
title: Cosmos3-Super-Text2Image (NVFP4)
emoji: 🌌
colorFrom: indigo
colorTo: purple
sdk: gradio
sdk_version: 6.15.1
app_file: app.py
python_version: "3.12"
short_description: NVIDIA Cosmos3-Super 64B text-to-image, NVFP4 quantization
startup_duration_timeout: 1h
pinned: false
license: other
---
Demo of [nvidia/Cosmos3-Super-Text2Image](https://huggingface.co/nvidia/Cosmos3-Super-Text2Image) — a 64B-parameter omnimodal text-to-image model — running on a single Blackwell GPU via NVFP4 weight-only quantization (NVIDIA ModelOpt).
NVIDIA officially tests this checkpoint only at BF16; NVFP4 is unofficial and may show quality drift compared to the full-precision recipe.