← Back to LLM Wiki
LLM Wiki · Open Weights · Self-Hostable

Gemma

Google's open-weights family — derived from Gemini research. Gemma 3, CodeGemma, PaliGemma, ShieldGemma.
Gemma is Google's answer to Llama: open-weights models built on the research and architecture that underpin Gemini, sized for self-hosted deployments (1B to 27B). Gemma 3 ships with native multimodality, strong multilingual coverage, and a permissive license that beats Llama's for most commercial use.
Google Open Weights Multimodal Multilingual Edge

Quick Facts

Vendor
Google DeepMind
Released
Gemma 1 (February 2024); Gemma 2 (June 2024); Gemma 3 (2025)
Current line
Gemma 3 (1B / 4B / 12B / 27B) · CodeGemma · PaliGemma · ShieldGemma
License
Gemma Terms of Use (permissive; commercial use allowed with a use-policy clause)
Hosting
Self-hosted (vLLM, Ollama, llama.cpp); Vertex AI; Kaggle; Hugging Face
Context window
128K tokens (Gemma 3)
Modalities
Text, vision (Gemma 3 native; PaliGemma specialized)
Architecture
Dense transformer based on Gemini research

Summary

Gemma is Google's open-weights line, launched in February 2024 as the open complement to Gemini. The models are trained on similar infrastructure and incorporate architectural choices from Gemini research, but ship with weights, permissive licensing, and a size range (1B–27B) aimed at self-hosted deployments. Gemma 3 (2025) added native multimodality and a 128K context window while keeping the same size-tier structure.

The family extends beyond the base text models. CodeGemma targets code workloads, PaliGemma is specialized for vision-language tasks, and ShieldGemma is the moderation classifier — Google's open answer to Llama Guard.

Model Lineup

Where Gemma Fits

Gemma is the default when the deployment is self-hosted and multilingual quality matters — Google's training data mix yields notably stronger non-English performance than most peers at similar size. The permissive Gemma Terms of Use beat Llama's Community License for many commercial scenarios (no 700M MAU clause). On a Mac Mini, Gemma 3 4B is a credible alternative to Qwen3 7B or Phi-4-mini.

Tradeoffs

Deployment Notes

Within the Claw ecosystem, Gemma 3 is a strong alternative to Qwen3 for customers who want a Google-lineage model self-hosted — often preferred where existing Google Cloud / Workspace relationships argue for architectural consistency. ShieldGemma is a drop-in alternative to Llama Guard in the FrawdBot preprocessing pipeline. For multilingual-heavy workloads (i18n support, non-English documentation), Gemma is often the best open-weights pick.

References

  1. Google — Gemma
  2. Google on Hugging Face
  3. ShieldGemma documentation
  4. Gemini — LLM Wiki
  5. The Agent Infrastructure Stack — Organized AI