Andreas
Phil2Sat
AI & ML interests
None yet
Organizations
None yet
fixing the text encoder issue for me
1
#30 opened 2 months ago
by
redbible666
'NoneType' object has no attribute 'device'
1
#24 opened 3 months ago
by
reportals21
Great job! Is there any update? Or can I try to quantify the conversion myself?
9
#22 opened 4 months ago
by
godkiss
patch on device does not work with this gguf
7
#1 opened 4 months ago
by
Zimdin12
The model took a full 10 minutes to load. Is it the same for you guys? I have 32GB of RAM and 16GB of VRAM.
4
#144 opened 4 months ago
by
Edward123a
V9 V10 need more VRAM, V5 can be run with 8G VRAM, but V9 V10 can't
11
#111 opened 4 months ago
by
richuyouyaojie
After using the quantized Qwen2.5-VL-7B-NSFW-Caption-V4.Q5_K_M.gguf model, the sampling always fails.
1
#20 opened 4 months ago
by
mrzmk
Is it possible to integrate qwen3vl into the model as CLIP?
9
#109 opened 4 months ago
by
q27916430
v9 Testing
👍 4
25
#102 opened 4 months ago
by
mystical8218
Can we continue to maintain it based on version 5.3?
👍 2
18
#103 opened 4 months ago
by
chyanbo
fp8_e5m2?
6
#98 opened 4 months ago
by
TheNecr0mancer
The v9 version looks better. Do you have plans to quantify it ?
6
#18 opened 4 months ago
by
chfm
comfyui0.3.68 causes image generation to fail.
18
#104 opened 4 months ago
by
ywchongjing
I would like to know how these gguf files are quantified?
2
#17 opened 4 months ago
by
chfm
What's the Point? [Learn More]
6
#1 opened 4 months ago
by
qpqpqpqpqpqp
A question for the author about Lightning LoRA model merging.
5
#95 opened 4 months ago
by
eternium
source quality
2
#15 opened 4 months ago
by
patientxtr
Please update mmproj metadata to clip-vision
1
#4 opened 4 months ago
by
Phil2Sat