bert bobson

bertbobson's activity

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

New activity in bertbobson/Z-Image-Turbo-INT8-Tensorwise 4 days ago

When converting fp16/bf16 diffuser models do you prefer int8 block-wise or tensor-wise

🚀 👀 1

1

#1 opened 4 days ago by

Winnougan

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 7 days ago

Will there be a chance to have INT4 later?

2

#4 opened 9 days ago by

someshijun

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 14 days ago

INT8V2 differences?

1

#3 opened 14 days ago by

DocterZed

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 17 days ago

What was the process to quantize?

2

#1 opened 17 days ago by

Lockout