B E

Smite79's activity

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

New activity in joeygambino/MiniMax-H3-encoder-GGUF about 11 hours ago

state_dict mismatch between the mmproj and the Q5_K_M GGUF

8

#1 opened 3 days ago by

Smite79

New activity in rzgar/minimax_h3_fl2va_fp8_e4m3fn about 24 hours ago

lora

2

#5 opened 6 days ago by

ludashi666

GGUF Q8 PLZ

2

#1 opened 6 days ago by

ass5002

New activity in Kijai/MiniMax-H3-TAE 2 days ago

madebyollin vae

4

#6 opened 4 days ago by

ohBeOne

how to use it as normal vae decode?

➕ 1

2

#10 opened 4 days ago by

shivshankar

New activity in ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot 3 days ago

could you please provide a WF for the genration tail int8 so i can try it out? thank you.

10

#5 opened 6 days ago by

necroryona

New activity in joeygambino/MiniMax-H3-Multishot-Workflow 3 days ago

Option to make it work with 4 step Lora?

1

#2 opened 3 days ago by

GeoSt77

liked a model 3 days ago

DmitryDB/MiniMax-H3-ComfyUI-Quants

Image-Text-to-Video • Updated 4 days ago • 18

New activity in DmitryDB/MiniMax-H3-ComfyUI-Quants 3 days ago

NVFP4 W4A4 Quantized?

#2 opened 3 days ago by

Smite79

liked a model 3 days ago

coolthor/MiniMax-H3-pruned-NVFP4

Image-Text-to-Video • Updated 5 days ago • 1.17k • 8

New activity in coolthor/MiniMax-H3-pruned-NVFP4 3 days ago

Awesome performance on an RTX 5060 Ti!

#1 opened 3 days ago by

Smite79

New activity in nif0/Qwen3-VL-32B-Instruct-ultra-uncensored-heretic-H3-GGUF 4 days ago

Not working - blows errors

2

#1 opened 4 days ago by

Smite79

New activity in ethanfel/Qwen3-VL-32B-Ultra-Heretic-H3-ComfyUI-INT8-ConvRot 4 days ago

not abliterated

5

#10 opened 4 days ago by

rzgar

updated a model 5 days ago

Smite79/LTX-2.3-RTX5060Ti

Text-to-Video • Updated 5 days ago

New activity in Comfy-Org/MiniMax-H3 5 days ago

Speedup 4-step LoRa ?

👀➕ 18

8

#11 opened 7 days ago by

joziku

New activity in Comfy-Org/MiniMax-H3 6 days ago

Please release an INT4-quantized version of MiniMax-H3

👍 4

9

#22 opened 6 days ago by

makisekurisu-jp

Approximating VAE? (Or video preview in general)

9

#20 opened 6 days ago by

inflatebot

New activity in Comfy-Org/MiniMax-H3 7 days ago

Will there be FP8 and NVFP4 of the models?

13

#5 opened 7 days ago by

VivekThePreceptor

the only thing i can say , LTX2.3 is like trash next to H3

👍 6

11

#8 opened 7 days ago by

agapes

New activity in unsloth/LTX-2.3-GGUF 9 days ago

Why it gives me OOM with 21gb gguf model but gens fine with 27gb fp8 safetensor?

👍 1

1

#12 opened 5 months ago by

Zuzuus