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
karantula
3
1
Follow
0 followers
ยท
1 following
AI & ML interests
None yet
Recent Activity
new
activity
6 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
8 days ago
unsloth/Qwen3.8-Flash-Next-GGUF:
4x slower than it should be? ๐ข
new
activity
8 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
karantula
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
New activity in
unsloth/Qwen3.8-Flash-Next-GGUF
6 days ago
Qwen3.8-Flash-Next: deep-context decode slowdown + top_k crash + MTP results (3x RTX 3090, full log)
4
#40 opened 8 days ago by
karantula
New activity in
unsloth/Qwen3.8-Flash-Next-GGUF
8 days ago
4x slower than it should be? ๐ข
๐ค
๐
5
13
#38 opened 8 days ago by
auf1r2
Qwen3.8-Flash-Next deep-context decode slowdown - CUDA multi-GPU reproduction (3x RTX 3090)
3
#39 opened 8 days ago by
karantula
liked
a model
22 days ago
Qwen/Qwen3.8-27B
Image-Text-to-Text
โข
28B
โข
Updated
22 days ago
โข
6.02M
โข
โข
14k