Uthman Bilal

Winnougan's activity

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

New activity in silveroxides/LTX-2.3-Quants about 23 hours ago

Dev INT8 version please?

🤝 1

#2 opened about 23 hours ago by

Winnougan

Does this work with your Comfyui nodes?

😎 1

4

#1 opened 5 days ago by

Winnougan

New activity in szwagros/ltx2.3-int8 3 days ago

Have you tested this in Comfyui?

😎 1

2

#1 opened 6 days ago by

Winnougan

New activity in cyankiwi/Qwen3.5-9B-AWQ-BF16-INT8 5 days ago

What's the best way to run AWQ models?

1

#1 opened 5 days ago by

Winnougan

New activity in Bedovyy/Anima-INT8 14 days ago

Regarding the loading of the model

4

#2 opened 18 days ago by

someshijun

New activity in bertbobson/Anima-INT8-QUIP 15 days ago

Output is a garbled mess

🤯 1

9

#2 opened 17 days ago by

Winnougan

New activity in DeepBeepMeep/Wan2.1 15 days ago

Can we get the INT8 treatment for all the Wan2.2 models?

#5 opened 15 days ago by

Winnougan

New activity in bertbobson/FLUX.2-klein-9B-INT8-Comfy 16 days ago

Can we get LTX-2 INT8?

#6 opened 16 days ago by

Winnougan

New activity in silveroxides/FLUX.2-dev-fp8_scaled about 1 month ago

Thanks for all the models. How to load the Small Mistral INT8 text encoder?

🔥 1

1

#10 opened about 1 month ago by

Winnougan

New activity in silveroxides/Wan_2.2-distilled-lightx2v-fp8_scaled_hybrid about 1 month ago

Could you provide the UMT5-XXL text encoder in INT8?

#1 opened about 1 month ago by

Winnougan

New activity in lightx2v/Qwen-Image-2512-Lightning about 1 month ago

How to use the int8 model

1

#7 opened 2 months ago by

xiilei99

New activity in bertbobson/Z-Image-Turbo-INT8-Tensorwise about 1 month ago

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

🔥 👀 1

1

#1 opened about 1 month ago by

Winnougan

New activity in GitMylo/Wan_2.2_nvfp4 about 1 month ago

Thanks man it works awesome

6

#4 opened about 1 month ago by

Winnougan

New activity in NSFW-API/NSFW-Wan-UMT5-XXL about 1 month ago

Please GGUF Quantize

🔥 3

3

#30 opened about 1 month ago by

MarioKartMTA

New activity in QuantFunc/Nunchaku-Qwen-Image-2512 about 2 months ago

Can you do Wan2.2 or LTX-2?

3

#3 opened about 2 months ago by

Winnougan

New activity in Orenguteng/Llama-3-8B-LexiFun-Uncensored-V1-GGUF about 2 months ago

Any new updates for 2026? Your models rock

1

#2 opened about 2 months ago by

Winnougan

New activity in nunchaku-ai/nunchaku 2 months ago

nunchaku-1.1.0+torch2.8-cp312-cp312-win_amd64.whl

👍 2

2

#5 opened 2 months ago by

makisekurisu-jp

New activity in diffusers/FLUX.2-dev-bnb-4bit 3 months ago

Does this work in Comfyui?

👍 1

3

#1 opened 3 months ago by

Winnougan

New activity in malcolmrey/zimage 3 months ago

Thanks bro!

🔥 4

9

#2 opened 3 months ago by

Winnougan

New activity in BigDannyPt/Illustrious-GGUF-Collection 4 months ago

How did you manage to make quants of these transformers?

🤝 1

1

#1 opened 4 months ago by

Winnougan