Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

google
/
gemma-4-26B-A4B-it

Image-Text-to-Text
Transformers
Safetensors
gemma4
conversational
Eval Results
Model card Files Files and versions
xet
Community
18
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Thank you Google!

1
#18 opened about 15 hours ago by
KngRnZ

[Appreciation] Incredible performance of Gemma 4-26b on consumer hardware — 90 t/s even on an older DDR3 system!

2
#17 opened 1 day ago by
MightyLoraLord

Excellent release, Google. Gemma 4 is good.

❤️ 2
2
#16 opened 1 day ago by
DorkMckork1

Fantastic release!

👍 5
1
#15 opened 3 days ago by
Dampfinchen

Significant Otter! ❤

🔥 3
2
#14 opened 4 days ago by
MrDevolver

THANK YOU! Google

❤️👍 7
1
#13 opened 5 days ago by
E7Reine

gemma

#12 opened 5 days ago by
Malay17b

Are you guys going to add other MoE stuff?

🤗 3
2
#11 opened 5 days ago by
Nesy1

Verified Commit?

2
#9 opened 6 days ago by
stephenrawls

please fp8

2
#8 opened 6 days ago by
huang123chuan

First community NVFP4 quantization of Gemma 4 26B-A4B-it (49GB → 16.5GB)

👍 1
2
#7 opened 6 days ago by
marioiseli

Add AIME 2026 evaluation result

#5 opened 6 days ago by
SaylorTwift

add eval results

#3 opened 6 days ago by
merve

error when batch size >1

#1 opened 27 days ago by
loulou2
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs