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 5 days ago

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

🚀 👀 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 15 days ago by

DocterZed

updated a model 16 days ago

bertbobson/Z-Image-Turbo-INT8-Tensorwise

Updated 16 days ago • 2

published a model 17 days ago

bertbobson/Z-Image-Turbo-INT8-Tensorwise

Updated 16 days ago • 2

updated a model 17 days ago

bertbobson/FLUX.2-klein-9B-INT8-Comfy

Updated 17 days ago • 8

updated a model 18 days ago

bertbobson/Chroma1-HD-INT8Tensorwise

Updated 18 days ago

published a model 18 days ago

bertbobson/Chroma1-HD-INT8Tensorwise

Updated 18 days ago

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 18 days ago

What was the process to quantize?

2

#1 opened 18 days ago by

Lockout

published a model 20 days ago

bertbobson/FLUX.2-klein-9B-INT8-Comfy

Updated 17 days ago • 8

updated a model 2 months ago

bertbobson/z_image_gguf

6B • Updated Nov 27, 2025 • 33 • 3

published a model 2 months ago

bertbobson/z_image_gguf

6B • Updated Nov 27, 2025 • 33 • 3