Oleg Kibirev

catplusplus's activity

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

published a model about 5 hours ago

catplusplus/MiniMax-M2.5-REAP-172B-A10B-NVFP4

Updated about 5 hours ago

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 7 days ago

VLLM + MTP + NVFP4 doesn't work

👀 1

1

#16 opened 7 days ago by

catplusplus

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 12 days ago

Run on DGX Spark

14

#14 opened 14 days ago by

LimeemiL

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 13 days ago

Doesn't work with latest vllm, even tried to recompile vLLM and transformers from git

➕ 1

4

#8 opened 17 days ago by

catplusplus

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 14 days ago

All this talk about NVFP4 - why is it dog slow?

13

#13 opened 15 days ago by

josephbreda

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 15 days ago

NVFP4 cannot be loaded in SGLang

4

#12 opened 16 days ago by

mratsim

New activity in nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 17 days ago

vLLM MTP unusable on RTX 6000 Pro, as spec decoding consumes 20GB+ VRAM at start-up, causing OOM

5

#9 opened 17 days ago by

lsmc

liked a model 25 days ago

llmfan46/Qwen3.5-35B-A3B-heretic-v2

Image-Text-to-Text • 35B • Updated 1 day ago • 3.17k • 25

updated a model 25 days ago

catplusplus/Qwen3.5-35B-A3B-heretic-NVFP4

Updated 25 days ago • 159

New activity in llmfan46/Qwen3.5-35B-A3B-heretic-v2 25 days ago

Made NVFP4 version

#3 opened 25 days ago by

catplusplus

updated a model 25 days ago

catplusplus/Qwen3.5-35B-A3B-heretic-v2-NVFP4

Updated 25 days ago • 870 • 3

published a model 25 days ago

catplusplus/Qwen3.5-35B-A3B-heretic-v2-NVFP4

Updated 25 days ago • 870 • 3

New activity in llmfan46/Qwen3.5-35B-A3B-heretic-v2 25 days ago

Got better even though the higher KLD!

👍 4

3

#2 opened 26 days ago by

FORNAX20

New activity in llmfan46/Qwen3.5-35B-A3B-heretic-v1 26 days ago

Any revision plan?

6

#2 opened 27 days ago by

Lck0427

Made catplusplus/Qwen3.5-35B-A3B-heretic-NVFP4 for Blackwell users

1

#3 opened 26 days ago by

catplusplus

published a model 26 days ago

catplusplus/Qwen3.5-35B-A3B-heretic-NVFP4

Updated 25 days ago • 159

updated a model about 2 months ago

catplusplus/Qwen-Image-2512-Heretic

8B • Updated Feb 9 • 34 • 2

published a model about 2 months ago

catplusplus/Qwen-Image-2512-Heretic

8B • Updated Feb 9 • 34 • 2

updated a model about 2 months ago

catplusplus/Qwen3-VL-30B-A3B-Instruct-Heretic-NVFP4

18B • Updated Feb 6 • 33 • 1

published a model about 2 months ago

catplusplus/Qwen3-VL-30B-A3B-Instruct-Heretic-NVFP4

18B • Updated Feb 6 • 33 • 1