infinity

infinityai's activity

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

liked a model about 4 hours ago

stepfun-ai/Step-3.5-Flash

Text Generation • 199B • Updated about 10 hours ago • 1.83k • 376

New activity in unsloth/Kimi-K2.5-GGUF 5 days ago

Can you make a REAP verson at 50

1

#4 opened 5 days ago by

infinityai

liked a model 7 days ago

moonshotai/Kimi-K2.5

Image-Text-to-Text • Updated about 12 hours ago • 123k • • 1.57k

New activity in meituan-longcat/LongCat-Flash-Thinking-2601 12 days ago

REAP & Auto Round

4

#5 opened 14 days ago by

infinityai

liked a model 13 days ago

unsloth/GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated 11 days ago • 299k • 405

New activity in 0xSero/GLM-4.6-REAP-218B-A32B-W4A16-AutoRound 14 days ago

Thank you for doing this one , I'm looking forward to the next one

#2 opened 14 days ago by

infinityai

liked a model 14 days ago

meituan-longcat/LongCat-Flash-Thinking-2601

Text Generation • 562B • Updated 11 days ago • 5.73k • 98

liked a model 15 days ago

mradermacher/GLM-4.7-REAP-218B-A32B-i1-GGUF

218B • Updated 15 days ago • 18.7k • 2

New activity in mradermacher/GLM-4.7-REAP-218B-A32B-i1-GGUF 15 days ago

Have you tried this compression technique?

#1 opened 15 days ago by

infinityai

liked a model 15 days ago

mradermacher/Qwen3-VL-REAP-145B-A22B-i1-GGUF

145B • Updated Dec 6, 2025 • 53 • 2

liked a model 17 days ago

Felladrin/gguf-Q2_K_S-Mixed-AutoRound-MiniMax-M2.1

229B • Updated 25 days ago • 181 • 5

liked a model 18 days ago

sasa2000/Qwen3-Coder-REAP-25B-A3B-int4-AutoRound

0.6B • Updated 24 days ago • 16 • 1

New activity in ubergarm/DeepSeek-V3.2-Speciale-GGUF 18 days ago

QuIP - 2 bit quantised as good as 16 bit

5

#5 opened 21 days ago by

infinityai

liked a model 21 days ago

bartowski/cerebras_GLM-4.7-REAP-218B-A32B-GGUF

Text Generation • 218B • Updated 22 days ago • 3.92k • 3

New activity in unsloth/GLM-4.7-REAP-218B-A32B 21 days ago

am looking forward to see what size gguf you can make

2

#1 opened 22 days ago by

infinityai

New activity in 0xSero/minimax-m2.1-reap-observations 21 days ago

QuIP - 2 bit compression as good as 16 bit

#1 opened 21 days ago by

infinityai

liked a model 28 days ago

0xSero/GLM-4.7-REAP-50-W4A16

Text Generation • 2B • Updated 29 days ago • 5.95k • 66

liked a model 30 days ago

Ex0bit/MiniMax-M2.1-PRISM

Text Generation • 229B • Updated 5 days ago • 17.2k • 97

upvoted a collection about 1 month ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 26 items • Updated 7 days ago • 99

New activity in ubergarm/Kimi-K2-Thinking-GGUF 3 months ago

Testing smol-IQ4_KSS

🚀 1

9

#8 opened 3 months ago by

shewin