artem

fogf's activity

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

New activity in Mapika/decider-0.8b about 2 hours ago

FP8 checkpoint for vLLM, measured against bf16

#2 opened about 2 hours ago by

fogf

New activity in Mapika/decider-2b about 2 hours ago

FP8 checkpoint for vLLM, measured against bf16

#3 opened about 2 hours ago by

fogf

New activity in Mapika/decider-4b about 2 hours ago

FP8 and NVFP4 checkpoints for vLLM, measured against bf16

#2 opened about 2 hours ago by

fogf

liked a model about 2 hours ago

llmtech/decider-4b-fp8

Text Classification • 4B • Updated about 3 hours ago • 2

updated a Space about 2 hours ago

Running

README

🔗

published a Space about 2 hours ago

Running

README

🔗

updated 2 models about 3 hours ago

llmtech/decider-4b-fp8

Text Classification • 4B • Updated about 3 hours ago • 2

llmtech/decider-4b-nvfp4

Text Classification • 2B • Updated about 3 hours ago • 1

liked 3 models about 3 hours ago

llmtech/decider-2b-fp8

Text Classification • 2B • Updated about 3 hours ago • 1

llmtech/decider-0.8b-fp8

Text Classification • 0.8B • Updated about 3 hours ago • 1

llmtech/decider-4b-nvfp4

Text Classification • 2B • Updated about 3 hours ago • 1

updated 2 models about 3 hours ago

llmtech/decider-2b-fp8

Text Classification • 2B • Updated about 3 hours ago • 1

llmtech/decider-0.8b-fp8

Text Classification • 0.8B • Updated about 3 hours ago • 1

published 4 models about 3 hours ago

llmtech/decider-0.8b-fp8

Text Classification • 0.8B • Updated about 3 hours ago • 1

llmtech/decider-2b-fp8

Text Classification • 2B • Updated about 3 hours ago • 1

llmtech/decider-4b-fp8

Text Classification • 4B • Updated about 3 hours ago • 2

llmtech/decider-4b-nvfp4

Text Classification • 2B • Updated about 3 hours ago • 1

New activity in Mapika/decider-4b about 7 hours ago

Subject: NVFP4 quant of decider-0.8b/2b/4b

#1 opened about 7 hours ago by

fogf

New activity in Qwen/Qwen3.8-27B about 1 month ago

Serving notes: prefix cache on the hybrid attention (1584-token blocks, lazy materialization) + thinking field gotchas

👍 3

#169 opened about 1 month ago by

fogf

liked a model about 1 month ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.73M • • 16.4k