Gemma 3 27B
Google's largest Gemma 3 open model with multimodal input, long context, and function calling for self-hosted stacks.
Pricing
InputOpen weights
Cached inputn/a
OutputSelf-hosted cost profile
No first-party token price because distribution is open-weight.
Cost bandFree/open
Free tierOpen weights; hosted cost depends on vendor.
Limits
Context window128k checked Jul 19, 2026
Max outputSee runtime
Knowledge cutoffSee model card
DeploymentSelf-hosted, Kaggle, Hugging Face, partner inference
OpenAI-compatible APIYes
ModalitiesText, Image input
Where it fits
Best forTeams that want Google lineage with open deployment and strong mid-to-large open-model utility.
Business fitUseful when data control or local deployment matters more than managed-service convenience.
Capabilities
Function calling140+ languagesOpen weightsMultimodal
Benchmark scores
Composite72 / 100
Coding70 / 100 (HumanEval)
Reasoning70 / 100 (MMLU-Pro)
Long context65 / 100
Vision76 / 100 (MMMU)
Instruction following72 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Jun 1, 2025. These are not independent measurements run by this site.
Change history
No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/google/gemma-3-27b-it
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.