eepos

eepos's activity

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

New activity in Kijai/Ming-Image-ComfyUI 2 days ago

int8 text-encoder erroring out

3

#1 opened 2 days ago by

eepos

New activity in Comfy-Org/YuE2 6 days ago

Is this model really open source?

👍 1

10

#6 opened 6 days ago by

adm1223

New activity in unsloth/Qwen3.8-27B-NVFP4 29 days ago

Please keep lm_head BF16

👀 6

4

#22 opened about 1 month ago by

codyknowscode

New activity in Lightricks/LTX-2.5 about 1 month ago

LTX 2.5 I2V basic workflow on ComfyUI is stuck forever if try to generate 10sec video

10

#15 opened about 1 month ago by

Mike128

New activity in Kijai/MiniMax-H3-experimental about 2 months ago

Why is int8_convrot VAE slower than fp16 VAE?

➕ 1

15

#21 opened about 2 months ago by

starmapking

Updated COMFY yesterday.... Do i need to update again today to use this model?

1

#2 opened about 2 months ago by

Liquidmind111

New activity in ggml-org/DeepSeek-V4-Flash-0731-GGUF about 2 months ago

Requesting Q2_K similar to one you made for the preview version of this model

1

#2 opened about 2 months ago by

eepos

New activity in unsloth/DeepSeek-V4-Flash-0731-GGUF about 2 months ago

Bug? UD-Q3_K_XL has one of the MXFP4 tensors converted to Q6_K

4

#7 opened about 2 months ago by

eepos

New activity in turboderp/Qwen3.6-27B-exl3 2 months ago

5bpw and 6bpw are in 4.00bpw tree

1

#1 opened 2 months ago by

eepos

New activity in Hippotes/Ideogram4-Fal-ComfyUI 2 months ago

difference between fast and instant?

3

#2 opened 2 months ago by

realrebelai

New activity in Comfy-Org/Ideogram-4 3 months ago

Flash attention optimization for significant speedup. - old title: Optimization tips to maximize generation speed?

16

#6 opened 4 months ago by

eepos

New activity in Winnougan/Krea-2-Base-Turbo-NVFP4-FP8-INT8 3 months ago

MXFP8 error: krea2 expects conditioning with 32x2560=81920 features (a 32-layer Qwen3-VL stack) but got 30720. Load the text encoder with CLIPLoader type 'krea2'.

5

#2 opened 3 months ago by

jtreminio

New activity in unsloth/gemma-4-26B-A4B-it-qat-GGUF 4 months ago

Gemma-4 QAT Special Unsloth quants

❤️ 4

10

#1 opened 4 months ago by

danielhanchen

New activity in Comfy-Org/Ideogram-4 4 months ago

Nvfp4 vs nf4

5

#3 opened 4 months ago by

realrebelai

do we need both models

11

#1 opened 4 months ago by

ryg81

New activity in unsloth/Step-3.7-Flash-GGUF 4 months ago

NEW MTP for Step 3.5 / 3.7 in Lama b9480

4

#6 opened 4 months ago by

Nerdsking

New activity in z-lab/MiniMax-M2.7-DFlash 5 months ago

approvals

👀 8

14

#1 opened 5 months ago by

cudaoom

New activity in Comfy-Org/HiDream-O1-Image 5 months ago

What is difference between fp8 scaled and mxfp8?

7

#4 opened 5 months ago by

shivshankar

New activity in Bedovyy/ERNIE-Image-Quantized 5 months ago

MXFP8?

2

#2 opened 5 months ago by

eepos

New activity in ubergarm/MiniMax-M2.7-GGUF 6 months ago

4bpw request =)

👀 1

13

#2 opened 6 months ago by

BahamutRU