Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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
kyunghyun roh's picture

kyunghyun roh

karantula
3 1
ยท

AI & ML interests

None yet

Recent Activity

new activity 11 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:Qwen3.8-Flash-Next: deep-context decode slowdown + top_k crash + MTP results (3x RTX 3090, full log)
new activity 12 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:4x slower than it should be? ๐Ÿข
new activity 12 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:Qwen3.8-Flash-Next deep-context decode slowdown - CUDA multi-GPU reproduction (3x RTX 3090)
View all activity

Organizations

None yet

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 11 days ago

Qwen3.8-Flash-Next: deep-context decode slowdown + top_k crash + MTP results (3x RTX 3090, full log)

4
#40 opened 12 days ago by
karantula
New activity in unsloth/Qwen3.8-Flash-Next-GGUF 12 days ago

4x slower than it should be? ๐Ÿข

๐Ÿค—๐Ÿ‘€ 5
13
#38 opened 13 days ago by
auf1r2

Qwen3.8-Flash-Next deep-context decode slowdown - CUDA multi-GPU reproduction (3x RTX 3090)

3
#39 opened 13 days ago by
karantula

Qwen3.8-Flash-Next deep-context decode slowdown - CUDA multi-GPU reproduction (3x RTX 3090)

3
#39 opened 13 days ago by
karantula
New activity in unsloth/Qwen3.8-Flash-Next-GGUF 13 days ago

Qwen3.8-Flash-Next deep-context decode slowdown - CUDA multi-GPU reproduction (3x RTX 3090)

3
#39 opened 13 days ago by
karantula
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs