dilavni

dilavni's activity

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

New activity in unsloth/Ornith-1.5-122B-GGUF 21 days ago

slower than qwen3.8 flash next on strix halo

3

#6 opened 22 days ago by

dilavni

New activity in unsloth/Qwen3.8-Flash-Next-GGUF about 1 month ago

llama.cpp now supports MTP in main, but these quants don't seem compatible

5

#79 opened about 1 month ago by

FlorinAndrei

n-gram from SSD: how exactly?

3

#75 opened about 2 months ago by

dilavni

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 2 months ago

4x slower than it should be? 🐢

🤗👀 5

13

#38 opened 3 months ago by

auf1r2

strix halo 128gb recommendations

21

#28 opened 3 months ago by

dilavni

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 3 months ago

Thinking Nightmare

🧠 2

10

#27 opened 3 months ago by

WhiteDan64

New activity in peculiar-ragdoll/Unsloth-Ornith-1.5-35B-A3B 3 months ago

Unsloth + No broken MTP

❤️ 2

10

#3 opened 3 months ago by

lolingface

New activity in ornith-ai/Ornith-1.5-35B-A3B-GGUF 3 months ago

Share your model speed here

4

#14 opened 3 months ago by

anvme

liked a model 3 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 5 days ago • 7.23M • • 19.6k

New activity in Myric/Laguna-S-2.1-APEX-GGUF 4 months ago

dflash drafter model load failure (on dflash q4_k or q8_0)

1

#6 opened 4 months ago by

dilavni

New activity in unsloth/Laguna-S-2.1-GGUF 4 months ago

llama.cpp chat template problems

#15 opened 4 months ago by

dilavni

llama.cpp chat template problems

#15 opened 4 months ago by

dilavni