Skip to main content

    Google (Gemma)

    Gemma 3

    The 27B variant of Google DeepMind's Gemma 3 open-weight family, announced March 12, 2025. This dense model accepts text and images, produces text and supports a 128K-token context window. Its weights are available for self-hosting and fine-tuning under the custom Gemma Terms of Use.

    128K tokens
    Multimodal
    Pro
    Provider
    Google (Gemma)
    Context
    128K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Pro
    Released
    Mar 12, 2025
    Speed
    Medium
    Reasoning
    Advanced
    Modality
    Multimodal

    Benchmarks

    Quality

    AA Intelligence Index
    4.9points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    10.1points
    Artificial Analysis · Date unknownAge unknown
    LiveCodeBench
    13.7%
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    42.8%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    118tokens/s
    Artificial Analysis · As of Aug 11, 2026Stale · 31d old

    API pricing

    API input cost
    $0.00/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $0.00/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: Gemma 3 27B Instruct

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Open Weights
    • Vision
    • Code
    • Fine-tuning
    • Self-hosting

    Use cases

    • On-prem AI
    • Custom fine-tuning
    • Data sovereignty
    • Edge deployment

    Strengths

    • Open weights
    • Text and image input
    • Gemma Terms of Use
    • 128K context

    Best for

    Organizations needing an open-weight, vision-capable model for self-hosted deployments

    Use Gemma 3 in yno.ai

    No credit card required

    Related models

    Frequently asked

    What is Gemma 3?
    The 27B variant of Google DeepMind's Gemma 3 open-weight family, announced March 12, 2025. This dense model accepts text and images, produces text and supports a 128K-token context window. Its weights are available for self-hosting and fine-tuning under the custom Gemma Terms of Use.
    How much does Gemma 3 cost in yno.ai?
    Gemma 3 is available on the Pro tier of yno.ai.
    What can Gemma 3 do?
    Gemma 3 is best for Organizations needing an open-weight, vision-capable model for self-hosted deployments. Its main capabilities include Open Weights, Vision, Code, Fine-tuning, Self-hosting.
    How does Gemma 3 compare to other models?
    Gemma 3 excels at Open weights and is recommended for On-prem AI, Custom fine-tuning, Data sovereignty, Edge deployment. See related models below.
    How do I use Gemma 3 in yno.ai?
    Sign up for yno.ai, select Gemma 3 from the model picker, and start chatting.