Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

google
/
gemma-4-12B

Any-to-Any
Transformers
Safetensors
gemma4_unified
image-text-to-text
Eval Results
Model card Files Files and versions
xet
Community
12

Instructions to use google/gemma-4-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • Transformers

    How to use google/gemma-4-12B with Transformers:

    # Load model directly
    from transformers import AutoProcessor, AutoModelForMultimodalLM
    
    processor = AutoProcessor.from_pretrained("google/gemma-4-12B")
    model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B", device_map="auto")
  • Notebooks
  • Google Colab
  • Kaggle
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Add Vaani-Benchmark-V1.0 eval results

#11 opened about 1 month ago by
PranavdbhatArtpark

Model doesn't support images in tool call outputs

1
#10 opened about 2 months ago by
dpe1

Vision👍

3
#9 opened about 2 months ago by
dpe1

Multimodality Parameters

#8 opened about 2 months ago by
yukiarimo

Vuk

4
#7 opened 2 months ago by
d3rlord3

Gemma 4 12B Unified zero-shot ASR underperforms Gemma 4 E4B on FLEURS

👀 6
#6 opened 2 months ago by
amor123hyk

By the Gods...

🤗 4
2
#2 opened 2 months ago by
JanjanJean

Installation Video and Testing - Step by Step

👍 3
1
#1 opened 2 months ago by
fahdmirzac
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs