Instructions to use google/gemma-4-12B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/gemma-4-12B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it") model = AutoModelForImageTextToText.from_pretrained("google/gemma-4-12B-it") - Notebooks
- Google Colab
- Kaggle
gemma 4 12b falsesly claims year
2
#31 opened about 4 hours ago
by
Tralalabs
Gemma4-12B Audio Deep Evaluation
2
#30 opened about 7 hours ago
by
PeterchanCN
How to use an assistent model for MTP in llama.cpp?
#29 opened about 9 hours ago
by
Regrin
Tool Calling and Tags and Context awareness.
#28 opened about 16 hours ago
by
JanjanJean
MLX 4-bit conversion of gemma-4-12B-it β with vision + audio embedder weights preserved
#27 opened 1 day ago
by
jokernifty
Gemma 4 124B DENSE + Nvidia N1x Laptop
#26 opened 1 day ago
by
87455a
What languages are supported in audio input?
π€ 1
1
#25 opened 3 days ago
by
J22
it is speaking Cantonese while user prompt is Simplified Chinese
3
#24 opened 3 days ago
by
leiyang88
Can't deploy on huggingface...
1
#23 opened 3 days ago
by
p-christ
NVFP4 Quant
1
#22 opened 3 days ago
by
berkerdooo
π Training support for transformers/megatron backends
1
#20 opened 3 days ago
by
study-hjt
NVFP4 / FP8 Quantizations
2
#19 opened 4 days ago
by
vincentzed-hf
Dimension mismatch crashes the engine at startup
π 1
1
#18 opened 4 days ago
by
CallShaul
Gemma 4 124b
π 18
7
#17 opened 4 days ago
by
FusionCow
Thank you Google team
π₯ 3
3
#16 opened 4 days ago
by
jreoka
Thanks again!
2
#15 opened 4 days ago
by
JanjanJean
MTP Assistant Model
1
#14 opened 4 days ago
by
patrickdeanbrown
I've been having a bunch of issues trying to do translations from Chinese to English
#13 opened 4 days ago
by
unlambda
Preserve the correct ordering of content and tool calls when rendering OpenAI Chat Completions
π 1
#12 opened 4 days ago
by
yzong-rh
Good, Google
π€π 4
5
#9 opened 4 days ago
by
dof-studio-org
Add HLE evaluation result
#7 opened 4 days ago
by
SaylorTwift
Add AIME 2026 evaluation result
#6 opened 4 days ago
by
SaylorTwift
Add MMMU Pro evaluation result
#5 opened 4 days ago
by
SaylorTwift
Add MMLU-Pro evaluation result
#4 opened 4 days ago
by
SaylorTwift
Add GPQA Diamond evaluation result
#3 opened 4 days ago
by
SaylorTwift
This is an awesome model proposition/idea for users with few VRAM.
π 2
2
#2 opened 4 days ago
by
Nesy1
Gemma 4:124b
ππ 88
18
#1 opened 4 days ago
by
seamon67