Ivan

fm3at's activity

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

New activity in VideoRebirthAI/hyperflow-h3-flash 4 days ago

FP16/BF16 for re-quanting?

6

#3 opened 7 days ago by

darksidewalker

New activity in krea/Krea-2-Turbo 12 days ago

VRAM

12

#2 opened 5 months ago by

AminTz

New activity in lightx2v/Qwen-Image-2.1-Lightning 28 days ago

This parameter combination is simply perfect, with 6 steps without noise

👀 1

2

#5 opened about 1 month ago by

HK-wang

liked a model about 2 months ago

ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF

Image-Text-to-Text • 177B • Updated Sep 29 • 7.02M • 1.25k

New activity in ISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUF about 2 months ago

Quick Comparison: ISTA-DASLab GSQ-RCO-IQ3_XXS vs unsloth UD-IQ4_XS on 4070Ti Super 16G + 64G RAM

15

#18 opened about 2 months ago by

BipedalBit

liked 3 models 2 months ago

ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF

Image-Text-to-Text • 27B • Updated Sep 2 • 1.35M • 2.83k

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 7 days ago • 6.76M • • 20k

F16/krea2-turbo-sda

Text-to-Image • Updated Aug 30 • 7.93k • • 118

New activity in unsloth/Qwen3.8-Flash-Next-GGUF 3 months ago

Is it possible to run it with a combined memory setup: 16 GB VRAM + 64 GB RAM + SSD for offloading n-grams?

6

#46 opened 3 months ago by

testtestad

liked a model 3 months ago

DmitryDB/MiniMax-H3-ComfyUI-Quants

Image-Text-to-Video • Updated Aug 5 • 39

liked a model 4 months ago

conradlocke/krea2-identity-edit

Updated 29 days ago • 281k • 960

New activity in conradlocke/krea2-identity-edit 4 months ago

NSFW edit

6

#33 opened 4 months ago by

lumosmaximaa

New activity in Comfy-Org/Pixal3D 4 months ago

missing core nodes

7

#1 opened 4 months ago by

vivi-gomez

New activity in krea/Krea-2-Turbo 5 months ago

The model was killed by the license.

3

#6 opened 5 months ago by

Czarj

New activity in Comfy-Org/Krea-2 5 months ago

The sampling acceleration from nvfp4 quantization in Krea2 is not significant.

15

#6 opened 5 months ago by

Aca233

New activity in Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8 5 months ago

Doesn't load

6

#1 opened 5 months ago by deleted

updated a model 6 months ago

fm3at/Sulphur-2-base-distil-nvfp4-mixed

Updated May 20 • 2

published a model 6 months ago

fm3at/Sulphur-2-base-distil-nvfp4-mixed

Updated May 20 • 2

New activity in nunchaku-ai/nunchaku-qwen-image-edit-2509 10 months ago

Anyone try it within 8GB VRAM?

5

#25 opened 10 months ago by

anonoob

New activity in unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF 10 months ago

Jan 12 2026: Qwen3-Next updated with iMatrix + Improved performance!

👍 3

26

#3 opened 11 months ago by

danielhanchen