Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Garrus Sun's picture

Garrus Sun

garrussun
1 2
webbrain-one-563425's profile picture
ยท

AI & ML interests

None yet

Recent Activity

liked a model 16 days ago
nvidia/DeepSeek-V4.1-Flash-NVFP4
liked a model 3 months ago
Qwen/Qwen3.8-27B
new activity 7 months ago
sakamakismile/Qwen3.6-27B-NVFP4:Qwen3.6-27B-NVFP4 is slower than official FP8 on Blackwell; possible fallback / FLA path mismatch on vLLM
View all activity

Organizations

None yet

liked a model 16 days ago

nvidia/DeepSeek-V4.1-Flash-NVFP4

Image-Text-to-Text โ€ข 763B โ€ข Updated 28 days ago โ€ข 33.2k โ€ข 129
liked a model 3 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text โ€ข 28B โ€ข Updated 5 days ago โ€ข 7.23M โ€ข โ€ข 19.6k
New activity in sakamakismile/Qwen3.6-27B-NVFP4 7 months ago

Qwen3.6-27B-NVFP4 is slower than official FP8 on Blackwell; possible fallback / FLA path mismatch on vLLM

๐Ÿ‘€ 2
8
#5 opened 7 months ago by
garrussun

Qwen3.6-27B-NVFP4 is slower than official FP8 on Blackwell; possible fallback / FLA path mismatch on vLLM

๐Ÿ‘€ 2
8
#5 opened 7 months ago by
garrussun
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs