Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
bert bobson's picture
5

bert bobson

bertbobson
Winnougan's profile picture balukumar's profile picture cocorang's profile picture
ยท

AI & ML interests

None yet

Recent Activity

new activity about 5 hours ago
coder3101/Qwen3-VL-8B-Thinking-heretic:Worthless.
new activity 5 days ago
bertbobson/Z-Image-Turbo-INT8-Tensorwise:When converting fp16/bf16 diffuser models do you prefer int8 block-wise or tensor-wise
new activity 8 days ago
bertbobson/FLUX.2-klein-9B-INT8-Comfy:Will there be a chance to have INT4 later?
View all activity

Organizations

None yet

New activity in coder3101/Qwen3-VL-8B-Thinking-heretic about 5 hours ago

Worthless.

โค๏ธ 1
#1 opened about 5 hours ago by
bertbobson
New activity in bertbobson/Z-Image-Turbo-INT8-Tensorwise 5 days ago

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

๐Ÿš€ ๐Ÿ”ฅ 1
1
#1 opened 5 days ago by
Winnougan
New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 8 days ago

Will there be a chance to have INT4 later?

2
#4 opened 10 days ago by
someshijun
New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 15 days ago

INT8V2 differences?

1
#3 opened 16 days ago by
DocterZed
New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 18 days ago

What was the process to quantize?

2
#1 opened 19 days ago by
Lockout
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs