Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Kijai
/
MiniMax-H3-experimental

Model card Files Files and versions
xet
Community
16
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Unprunned model versions w4a8 request

#16 opened about 1 hour ago by
boricuapab

w4a8 slower than int8??

1
#15 opened about 3 hours ago by
Fronyax

question about format and running in comfy

2
#14 opened about 12 hours ago by
realrebelai

minimax_h3_video_vae_int8_convrot.safetensors

13
#13 opened about 15 hours ago by
Portland01

Custom node required?

3
#9 opened 2 days ago by
MJS255

Update README.md

#8 opened 2 days ago by
ryanlee-dev

KeyError: 'asym_w4a8_int8'

2
#7 opened 2 days ago by
Danzelus

VRAM savings?

#6 opened 2 days ago by
pizzawookiee

I found MiniMax-H3-Turbo-Lora ~ 4-step

❤️👍 1
2
#5 opened 2 days ago by
sunnyboxs

Great work! Please also make one for the ref2va version. Thanks!

👍 7
6
#4 opened 2 days ago by
lucas-ai26

finally!

1
#3 opened 3 days ago by
Kutches

Is pruned_w4a8_mixed identical to a4w8_codebook?

2
#1 opened 3 days ago by
makisekurisu-jp
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs