·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Treasury threatens sanctions after White House claims Moonshot distilled Anthropic’s Fable25m◆How OpenAI’s human mistake led to the AI-powered hack on Hugging Face2h◆Travis Kalanick’s robotics company raises $1.7B, led by a16z2h◆Yope raises $12.3M to build a private social network without algorithms or ads3h◆Monday.com lays off hundreds to focus on AI3h◆Here’s what Samsung’s smart glasses actually look like4h◆Arcee, a US open source AI lab, says Chinese models are not inherently dangerous4h◆Substack’s new tool tells you who’s been writing their newsletters with AI4h◆OpenAI’s AI spending spree has ballooned to $750B5h◆AMD commits up to $5 billion to Anthropic6h◆Menlo Ventures’ Matt Murphy explains what AI startups founders must do differently7h◆The browser wars aren’t about search anymore — here are the best alternatives to Chrome and Safari7h◆Building AI infrastructure with the Effingham County community8h◆3 Google updates from Galaxy Unpacked 20268h◆Passionfroot raises $15M to expand its B2B creator marketplace to the US8h◆How news organizations are using AI to advance their vital missions8h◆Advancing the next era of national science9h◆Meta made its own AI detection system. It should have just used Google’s10h◆Utility companies promise to spare us from AI’s energy bill11h◆Glow emerges from stealth at $1.2B valuation to challenge endpoint security in the AI era11h◆Treasury threatens sanctions after White House claims Moonshot distilled Anthropic’s Fable25m◆How OpenAI’s human mistake led to the AI-powered hack on Hugging Face2h◆Travis Kalanick’s robotics company raises $1.7B, led by a16z2h◆Yope raises $12.3M to build a private social network without algorithms or ads3h◆Monday.com lays off hundreds to focus on AI3h◆Here’s what Samsung’s smart glasses actually look like4h◆Arcee, a US open source AI lab, says Chinese models are not inherently dangerous4h◆Substack’s new tool tells you who’s been writing their newsletters with AI4h◆OpenAI’s AI spending spree has ballooned to $750B5h◆AMD commits up to $5 billion to Anthropic6h◆Menlo Ventures’ Matt Murphy explains what AI startups founders must do differently7h◆The browser wars aren’t about search anymore — here are the best alternatives to Chrome and Safari7h◆Building AI infrastructure with the Effingham County community8h◆3 Google updates from Galaxy Unpacked 20268h◆Passionfroot raises $15M to expand its B2B creator marketplace to the US8h◆How news organizations are using AI to advance their vital missions8h◆Advancing the next era of national science9h◆Meta made its own AI detection system. It should have just used Google’s10h◆Utility companies promise to spare us from AI’s energy bill11h◆Glow emerges from stealth at $1.2B valuation to challenge endpoint security in the AI era11h◆
News/model/Wan2.2-NVFP4-Sparse

Wan2.2-NVFP4-Sparse news

3 articles mentioning Wan2.2-NVFP4-Sparse

arxivJun 2

Collaborative Few-Step Distillation and Low-Bit Quantization for Wan2.2 Dual-Expert Video Diffusion Models

arXiv:2606.00658v1 Announce Type: cross Abstract: Large video diffusion models achieve strong visual quality but remain expensive to deploy because each sample requires many denoising steps and a large resident parameter footprint. This paper studies a deployment-oriented compression pipeline for Wa

arxivMay 27

Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

arXiv:2605.27003v1 Announce Type: cross Abstract: W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-st

arxivMay 27

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

arXiv:2605.26628v1 Announce Type: new Abstract: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantization pipeline to Wan2.2 under the HiFloat4 numerical format. We quantiz

HomeModelsNews