JnJn

jnjn's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 13 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 13 days ago • 3.46M • • 13k

New activity in AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4 2 months ago

Any clues on why it is so much slower (no DFlash, no MTP state) than Qwen 3.6 35b? ~35 vs 70 (50% vs 100%)

1

#1 opened 2 months ago by

jnjn

liked a model 2 months ago

AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4

Text Generation • 21B • Updated Jul 15 • 4.9k • 58

liked a model 5 months ago

cyankiwi/gemma-4-31B-it-AWQ-4bit

Image-Text-to-Text • 33B • Updated Jul 21 • 273k • 52