Oleg Kibirev

catplusplus's activity

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

New activity in nunchaku-ai/nunchaku-z-image-turbo 3 days ago

Ported nuchaku to triton kernels for NVIDIA Thor (sm_110) compatibility, would need community help to polish

#13 opened 3 days ago by

catplusplus

updated a model 13 days ago

catplusplus/Qwen3-Omni-30B-A3B-Thinking-heretic-NVFP4

19B • Updated 12 days ago • 46

published a model 13 days ago

catplusplus/Qwen3-Omni-30B-A3B-Thinking-heretic-NVFP4

19B • Updated 12 days ago • 46

updated 2 models 17 days ago

catplusplus/Qwen3-Omni-30B-A3B-Instruct-NVFP4

23B • Updated 17 days ago • 87

catplusplus/Qwen3-Omni-30B-A3B-Instruct-NVFP4-talker-safe

29B • Updated 17 days ago • 70

published a model 17 days ago

catplusplus/Qwen3-Omni-30B-A3B-Instruct-NVFP4-talker-safe

29B • Updated 17 days ago • 70

published a model 22 days ago

catplusplus/Qwen3-Omni-30B-A3B-Instruct-NVFP4

23B • Updated 17 days ago • 87

updated a model 26 days ago

catplusplus/Qwen3.6-27B-uncensored-heretic-v2-NVFP4-MTP

Updated 26 days ago • 842

New activity in catplusplus/Qwen3.6-27B-uncensored-heretic-v2-NVFP4-MTP 28 days ago

Update README.md

#1 opened 28 days ago by

catplusplus

published a model 28 days ago

catplusplus/Qwen3.6-27B-uncensored-heretic-v2-NVFP4-MTP

Updated 26 days ago • 842

New activity in saricles/MiniMax-M2.7-REAP-172B-A10B-BF16 about 1 month ago

Pathname confusion

#1 opened about 1 month ago by

catplusplus

New activity in saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 about 1 month ago

Made a version with full precision attention and kv cache scales

3

#1 opened about 1 month ago by

catplusplus

updated a model about 1 month ago

catplusplus/MiniMax-M2.7-REAP-172B-A10B-NVFP4

Text Generation • 116B • Updated Apr 18 • 221 • 1

published a model about 1 month ago

catplusplus/MiniMax-M2.7-REAP-172B-A10B-NVFP4

Text Generation • 116B • Updated Apr 18 • 221 • 1

New activity in llmfan46/gemma-4-31B-it-uncensored-heretic about 1 month ago

Would you consider model adoption to solve your storage issues?

1

#2 opened about 1 month ago by

catplusplus

New activity in coder3101/Qwen3.5-122B-A10B-heretic-v2 about 1 month ago

quantizing to MLX 4bit removed abliteration

9

#2 opened 3 months ago by

giediprime

do the same thing you did with 27b because it does a lot better.

1

#3 opened 2 months ago by

drmcbride

New activity in coder3101/Qwen3.5-122B-A10B-heretic-v2 about 2 months ago

Uploaded an NVFP4 quant for Thor/Spark

#5 opened about 2 months ago by

catplusplus

updated a model about 2 months ago

catplusplus/Qwen3.5-122B-A10B-heretic-v2-NVFP4

71B • Updated Apr 8 • 48

published a model about 2 months ago

catplusplus/Qwen3.5-122B-A10B-heretic-v2-NVFP4

71B • Updated Apr 8 • 48