ModelsModel releaseImage, Video & 3D Generation · Efficiency & Inference · Computer Vision1 source · Oct 9, 2026

nvidia/Qwen-Image-NVFP4

nvidia published the model Qwen-Image-NVFP4 on Hugging Face.

NVIDIAQwenHugging FaceDiffusersnvidia/Qwen-Image-NVFP4
ProofWeights ↗
Read at HF: NVIDIA ↗← Today

Sources (1)

  • [1]nvidia/Qwen-Image-NVFP4
    HF: NVIDIA · Oct 9, 11:37 PM
    nvidia published the model Qwen-Image-NVFP4 on Hugging Face.

Extractive summary: sentences quoted from the sources.

Before this

  1. Oct 9, 2026DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
  2. Oct 9, 2026Qwen/Qwen-Image-2.1-Turbo
  3. Oct 9, 2026Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
  4. Oct 8, 2026unslothai/unsloth v0.1.905-beta: Sandboxing is here!
  5. Oct 8, 2026DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
  6. Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0

Related

HF: NVIDIA10d ago

nvidia/PixelUMM

Weights
HF: NVIDIA10d ago

nvidia/PixelDiT2-ImageNet

Weights
GitHub: huggingface/diffusers6d ago

huggingface/diffusers v0.41.0: Diffusers 0.41.0: QwenImage 2.1 pipeline and more

Code
HF: NVIDIA2d ago

nvidia/agile_one_s_place_ssd_n17_24050

Weights