bert bobson

bertbobson's activity

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

updated a model 1 day ago

bertbobson/ComfyUI-INT8_ConvRot

Updated 1 day ago • 2

published a model 1 day ago

bertbobson/ComfyUI-INT8_ConvRot

Updated 1 day ago • 2

New activity in wikeeyang/Magic-Wan-T2IV-V3 2 days ago

BF16/FP16 Version

3

#3 opened 29 days ago by

UbuUbu

New activity in kandinskylab/KVAE-3D-2.0-t4s8 9 days ago

Is this the VAE for Kandinsky 6.0? When will Kandinsky 6.0 be released?

🤯 1

3

#1 opened 29 days ago by

BestWishYsh

New activity in NucleusAI/Nucleus-Image 29 days ago

Diffusers example for low vram?

👀👍 4

6

#2 opened 29 days ago by

bertbobson

updated a model about 1 month ago

bertbobson/Qwen3.5-27B-bnb-4bit

28B • Updated Apr 2 • 434

published a model about 2 months ago

bertbobson/Qwen3.5-27B-bnb-4bit

28B • Updated Apr 2 • 434

New activity in bertbobson/Anima-INT8-QUIP 2 months ago

Output is a garbled mess

🤯 1

13

#2 opened 3 months ago by

Winnougan

updated 2 models 2 months ago

bertbobson/Anima-INT8-QUIP

Updated Feb 28

bertbobson/Z-Image-Base-INT8-QUIP

Updated Feb 28 • 1

published a model 2 months ago

bertbobson/Z-Image-Base-INT8-QUIP

Updated Feb 28 • 1

New activity in unsloth/Qwen3.5-27B 3 months ago

Will there be a dynamic bnb quantized version?

2

#1 opened 3 months ago by

bertbobson

New activity in bertbobson/Anima-INT8-QUIP 3 months ago

Sorry, may I know how to use Anima with your nodes? I can only get some garbled codes.

1

#1 opened 3 months ago by

someshijun

published a model 3 months ago

bertbobson/Anima-INT8-QUIP

Updated Feb 28

New activity in vistralis/FLUX.2-klein-base-9b-INT8-transformer 3 months ago

Any chance you could share the workflow you used to create these models with ModelOpt?

#1 opened 3 months ago by

bertbobson

New activity in coder3101/Qwen3-VL-8B-Thinking-heretic 3 months ago

Worthless.

❤️🤯 2

#1 opened 3 months ago by

bertbobson

New activity in bertbobson/Z-Image-Turbo-INT8-Tensorwise 3 months ago

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

👀🔥 1

1

#1 opened 3 months ago by

Winnougan

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 3 months ago

Will there be a chance to have INT4 later?

2

#4 opened 3 months ago by

someshijun

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 4 months ago

INT8V2 differences?

1

#3 opened 4 months ago by

DocterZed

updated a model 4 months ago

bertbobson/Z-Image-Turbo-INT8-Tensorwise

Updated Jan 24 • 3