google/gemma-4-31B-it · Discussions

#34 opened about 5 hours ago by

MarcosFRGames

Fantastic Model for Legal/English Language Use Cases

#33 opened about 8 hours ago by

md-1415

test it yourself

#32 opened about 18 hours ago by

rosspanda0

It can't edit code!!

3

#31 opened 1 day ago by

JoeSmith245

RuntimeError: FlashAttention forward only supports head dimension at most 256

#30 opened 1 day ago by

badhon1512

Can you guys make a smaller dense?

6

#29 opened 1 day ago by

Nesy1

Missing 'reasoning' field in response when serving gemma-4-31B-it with vLLM

6

#28 opened 2 days ago by

Iann

Community resources for Gemma 4 deployment — mobile, local, and cloud paths

#27 opened 2 days ago by

Linncharm

trying

#26 opened 2 days ago by

tiiihzx

aav

#25 opened 2 days ago by

tiiihzx

a

#24 opened 2 days ago by

tiiihzx

Unable to view the model file the architecture!

#23 opened 2 days ago by

naren-1219

The first small model for honest conversation

👍 6

#22 opened 3 days ago by

ghostwithahat

Please, Google open-source the ancient model "Gemini 1.0 Pro". Please, devepoler comment and share with google.

#21 opened 3 days ago by

Tralalabs

Fix Gemma4 `response_schema` regex to capture content after tool calls

👀 1

#19 opened 3 days ago by

qgallouedec

..but where's the bigger one?

👍 2

#18 opened 3 days ago by

jerryblunder

This model didn't release, it escaped 💀🫪

🔥👍 6

#17 opened 3 days ago by

evewashere

🚀测评视频+OpenClaw中使用方式

#16 opened 4 days ago by

leo009

Model seems to have issues in vLLM (characters duplication)

🔥 1

#15 opened 4 days ago by

dehnhaide

Is a QAT fine-tune planned?

👀🔥 18

#14 opened 4 days ago by

stduhpf

What is the training precision of Gemma 4? (bf16?)

👍 2

#13 opened 4 days ago by

hyunmin253

Why Gemma4 can't recognize the entire text on image?

🚀 4

6

#12 opened 4 days ago by

alexcardo

About the video understanding?

#11 opened 4 days ago by

Alexander-2

124B, pretty please?

👍 15

#10 opened 4 days ago by

vody-am

Sentencepiece model file

#9 opened 4 days ago by

Bingsu

Are you insane to push agenda into local model?

🤯❤️ 17

9

#8 opened 4 days ago by

Krokozor

Any params/containers to deploy it from HF Inference Endpoints?

👀 1