catplusplus/Qwen3.5-122B-A10B-heretic-v2-NVFP4
71B • Updated • 103
Oleg Kibirev
catplusplus
AI & ML interests
None yet
Recent Activity
new activity 37 minutes ago
coder3101/Qwen3.5-122B-A10B-heretic-v2:quantizing to MLX 4bit removed abliteration new activity about 1 hour ago
coder3101/Qwen3.5-122B-A10B-heretic-v2:do the same thing you did with 27b because it does a lot better. new activity 3 days ago
coder3101/Qwen3.5-122B-A10B-heretic-v2:Uploaded an NVFP4 quant for Thor/SparkOrganizations
None yet
models 8
catplusplus/MiniMax-M2.5-REAP-172B-A10B-NVFP4
116B • Updated • 76 • 1
catplusplus/Qwen3.5-35B-A3B-heretic-v2-NVFP4
Updated • 1.12k • 4
catplusplus/Qwen-Image-2512-Heretic
8B • Updated • 28 • 3
catplusplus/Qwen3-VL-30B-A3B-Instruct-Heretic-NVFP4
18B • Updated • 7 • 1
catplusplus/Qwen3-VL-30B-A3B-Instruct-Heretic
31B • Updated • 4 • 1
catplusplus/Qwen3-VL-30B-A3B-Thinking-Heretic-NVFP4
18B • Updated • 2
catplusplus/Qwen3-VL-30B-A3B-Thinking-Heretic
Image-Text-to-Text • 31B • Updated • 61 • 1
datasets 0
None public yet