google/gemma-4-12B-it · Discussions

#45 opened 10 days ago by

frandagostino

SAE for this model?

#44 opened 11 days ago by

joggyback

Add response_template to tokenizer_config.json

#43 opened 20 days ago by

Rocketknight1

https://share.gemini.google/7T1rHMOMMfPH

#42 opened 22 days ago by

DIGITALLEADERSHIP

gemma-4-12B-it: deterministic "thought\n thought\n …" degenerate loop on long agent prompts (~60% reproducer, 4-bit, repros across temperatures)

9

#41 opened about 1 month ago by

Raullen

Fairly Useless

👍 3

4

#40 opened about 1 month ago by

yano2mch

Gemma 4 12b bias affraid me

#39 opened about 1 month ago by

Alekto

Chat template may re-inject prior-turn reasoning during multi-turn tool use → repetition loops

5

#38 opened about 1 month ago by

ManniX-ITA

fdsfsdfsdfdf

#37 opened about 1 month ago by

jiwang1

asfd

#36 opened about 1 month ago by

jiwang1

Gemma 4 124b, please!

🚀🔥 9

4

#34 opened about 1 month ago by

slavczays

vllm support?

3

#32 opened about 1 month ago by

mohamedemam

gemma 4 12b falsesly claims year

#31 opened about 1 month ago by

Tralalabs

Gemma4-12B Audio Deep Evaluation

#30 opened about 1 month ago by

PeterchanCN

How to use an assistent model for MTP in llama.cpp?

#29 opened about 1 month ago by

Regrin

Tool Calling and Tags and Context awareness.

👍 1

#28 opened about 1 month ago by

JanjanJean

MLX 4-bit conversion of gemma-4-12B-it — with vision + audio embedder weights preserved

#27 opened about 1 month ago by

jokernifty

Gemma 4 124B DENSE + Nvidia N1x Laptop

❤️🔥 2

#26 opened about 1 month ago by

87455a

What languages are supported in audio input?

🤝 1

#25 opened about 1 month ago by

J22

it is speaking Cantonese while user prompt is Simplified Chinese

3

#24 opened about 1 month ago by

leiyang88

Can't deploy on huggingface...

#23 opened about 2 months ago by

p-christ

NVFP4 Quant

#22 opened about 2 months ago by

berkerdooo

👋 Training support for transformers/megatron backends

#20 opened about 2 months ago by

study-hjt

NVFP4 / FP8 Quantizations

#19 opened about 2 months ago by

vincentzed-hf

Dimension mismatch crashes the engine at startup

👍 2

#18 opened about 2 months ago by

CallShaul

Gemma 4 124b

🚀 20

10

#17 opened about 2 months ago by

FusionCow

Thank you Google team

❤️🔥 5

4

#16 opened about 2 months ago by

jreoka

Thanks again!

❤️ 1

3

#15 opened about 2 months ago by

JanjanJean

MTP Assistant Model

#14 opened about 2 months ago by

patrickdeanbrown

Preserve the correct ordering of content and tool calls when rendering OpenAI Chat Completions

👀 1

#12 opened about 2 months ago by

yzong-rh

Good, Google

🤝👍 4

5

#9 opened about 2 months ago by

dof-studio-org

Add HLE evaluation result

#7 opened about 2 months ago by

Add AIME 2026 evaluation result

#6 opened about 2 months ago by

Add MMMU Pro evaluation result

#5 opened about 2 months ago by

Add MMLU-Pro evaluation result

#4 opened about 2 months ago by

Add GPQA Diamond evaluation result

#3 opened about 2 months ago by

This is an awesome model proposition/idea for users with few VRAM.

🚀 2