bae
baesik
·
AI & ML interests
None yet
Recent Activity
liked a model 21 days ago
dummy9996/qwen3-vl-comfyui-w4a8 liked a model 21 days ago
Winnougan/Klein9b-Distilled-Base-INT8-Convrot new activity 21 days ago
ussoewwin/Flash-Attention-2_for_Windows:PyTorch 2.13.0 + CUDA 13.2 [13.3?]Organizations
PyTorch 2.13.0 + CUDA 13.2 [13.3?]
#9 opened about 2 months ago
by
baesik
Have you tried silveroxides/convert_to_quant ?
1
#3 opened about 1 month ago
by
baesik
Krea2-Turbo-int8-ConvRot.safetensors vs released official
1
#5 opened about 2 months ago
by
baesik
which krea2bypass do you recommend?
👍 4
1
#1 opened 2 months ago
by
Kutches
Requesting int8_convrot text encoder
#9 opened about 2 months ago
by
baesik
Requesting: quantized fp8 mixed, nvfp4
#14 opened 2 months ago
by
baesik
ComfyUI and fp4 (Blackwell) plans?
2
#4 opened 10 months ago
by
baesik
2025 Update?
#12 opened 10 months ago
by
baesik
svdq-fp4_r32-shuttle-jaguar.safetensors crash in ComfyUI?
#2 opened 10 months ago
by
baesik
Creating our own "pig" ggufs?
1
#3 opened 10 months ago
by
baesik
Flash Attention cu130 torch 2.9 cp312 missing
👍 2
4
#4 opened 10 months ago
by
baesik
Add Nightly Versions of PyTorch, TorchAudio, TorchVision, and xFormers (with CUDA Support)
7
#3 opened 11 months ago
by
donn22
gguf comfyui inference error
1
#4 opened about 1 year ago
by
baesik
What's the difference between all these t5XXL models?
1
#2 opened about 1 year ago
by
baesik
Quick question about your quantized Q8 model vs another
1
#1 opened about 1 year ago
by
baesik