← Back to hard AIs

Verify critical details — pricing, licensing, availability — with the model's source before business decisions. Full methodology →

Models · Google

Feature-frozen. The creator has frozen feature development on this model (critical fixes only).

Gemma 3 12B

Model family: gemma-3

The 12B Gemma 3 — a single-GPUThe specialized chip that runs most AI models. Originally designed for 3D graphics, GPUs turned out to be excellent at the math AI requires. Nvidia dominates the AI GPU market; common datacenter models include the H100, H200, and B200. Running an AI model without a GPU is possible but painfully slow for anything but the smallest models. mid-size under the custom Gemma Terms of Use, superseded by Gemma 4.

Identity

Creator
Google
Model family
gemma-3
Release date
2025-03-11

Technical specs

Parameter count
12B
Context window
131K tokens
Modalities
  • Image Input
  • Text
Primary capabilities
  • Chat
  • Instruction Following
  • Multilingual
  • Reasoning
  • Vision

License

License
Gemma Terms of Use
Commercial use
  • Allowed
Terms
  • Modification
  • Redistribution
  • Attribution

Access

Openness
  • Open Weight
Access methods
  • Local Runtime Llama Cpp
  • Local Runtime Lm Studio
  • Local Runtime Ollama
  • Local Runtime Vllm
  • Weights Download Hf
Cost tier
  • Mixed

Full model card →