ai/gemma3

Verified Publisher

By Docker

Updated 6 months ago

Google’s latest Gemma, small yet strong for chat and generation

Model
58

500K+

ai/gemma3 repository overview

Gemma 3

GGUF version by Unsloth

logo

Gemma is a versatile AI model family designed for tasks like question answering, summarization, and reasoning. With open weights and responsible commercial use, it supports image-text input, a 128K token context, and over 140 languages.

Intended uses

Gemma 3 4B model can be used for:

  • Text generation: Create poems, scripts, code, marketing copy, and email drafts.
  • Chatbots and conversational AI: Enable virtual assistants and customer service bots.
  • Text summarization: Produce concise summaries of reports and research papers.
  • Image data extraction: Interpret and summarize visual data for text-based communication.
  • Language learning tools: Aid in grammar correction and interactive writing practice.
  • Knowledge exploration: Assist researchers by generating summaries and answering questions.

Characteristics

AttributeDetails
ProviderGoogle DeepMind
ArchitectureGemma3
Cutoff date-
Languages140 languages
Tool calling
Input modalitiesText, Image
Output modalitiesText, Code
LicenseGemma Terms

Available model variants

Model variantParametersQuantizationContext windowVRAM¹Size
ai/gemma3:4B

ai/gemma3:4B-Q4_K_M

ai/gemma3:latest
4BMOSTLY_Q4_K_M131K tokens3.83 GiB2.31 GB
ai/gemma3:270M-F16270MMOSTLY_F1633K tokens1.59 GiB511.46 MB
ai/gemma3:270M-UD-IQ2_XXS270MMOSTLY_IQ2_XXS33K tokens1.26 GiB165.54 MB
ai/gemma3:270M-UD-Q4_K_XL270MMOSTLY_Q4_K_M33K tokens1.33 GiB235.95 MB
ai/gemma3:4B-F164BMOSTLY_BF16131K tokens8.75 GiB7.23 GB

¹: VRAM estimated based on model characteristics.

latest4B

Use this AI model with Docker Model Runner

First, pull the model:

docker model pull ai/gemma3

Then run the model:

docker model run ai/gemma3

For more information on Docker Model Runner, explore the documentation.

Benchmark performance

CategoryBenchmarkValue
GeneralMMLU59.6
GSM8K38.4
ARC-Challenge56.2
BIG-Bench Hard50.9
DROP60.1
STEM & CodeMATH24.2
MBPP46.0
HumanEval36.0
MultilingualMGSM34.7
Global-MMLU-Lite57.0
XQuAD (all)68.0
MultimodalVQAv263.9
TextVQA58.9
DocVQA72.8

Tag summary

Content type

Model

Digest

sha256:a353a8898

Size

3.1 GB

Last updated

6 months ago

docker model pull ai/gemma3

This week's pulls

Pulls:

12,220

Last week