Resources

fix: function calling formatting in chat template

#20 opened about 16 hours ago by

RyanMullins

Vertex AI & vLLM Deployment Guide for Gemma 4 26B-A4B-it (MoE) + Known Limitations

🚀❤️ 1

#19 opened about 20 hours ago by

Manzela-D

Thank you Google!

#18 opened 2 days ago by

KngRnZ

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

#17 opened 2 days ago by

MightyLoraLord

Excellent release, Google. Gemma 4 is good.

❤️ 2

#16 opened 3 days ago by

DorkMckork1

Fantastic release!

👍 5

#15 opened 5 days ago by

Dampfinchen

Significant Otter! ❤

🔥 3

#14 opened 6 days ago by

MrDevolver

THANK YOU! Google

❤️👍 7

#13 opened 6 days ago by

E7Reine

gemma

#12 opened 6 days ago by

Malay17b

Are you guys going to add other MoE stuff?

🤗 3

#11 opened 6 days ago by

Nesy1

Verified Commit?

#9 opened 7 days ago by

stephenrawls

please fp8

#8 opened 7 days ago by

huang123chuan

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

👍 1

#7 opened 7 days ago by

marioiseli

Add AIME 2026 evaluation result

#5 opened 8 days ago by

SaylorTwift

add eval results

#3 opened 8 days ago by

merve

error when batch size >1

#1 opened 29 days ago by

loulou2