← Back to directory
Google DeepMind · Released 2025-11

Gemma 3

Google's open-weight family. The 2B variant is one of the strongest small models — runs on phones, edge devices, even a Raspberry Pi 5.

GemmaCommercial use OK👁 Visiongeneralsmall
Params (max)
27B
Variants
27B / 9B / 2B
Context window
128K tokens
MMLU
78.5
HumanEval
71.2
GSM8K
86.5
Min VRAM (fp16, smallest variant)
6GB
Smallest Q4 GGUF
~1.6GB
Languages supported
35
Pros
  • Best-in-class small models
  • Backed by Google
  • Permissive Gemma license
Cons
  • ×Not the smartest in its size class for code
  • ×Gemma license has prohibited-use clauses

Highlights

  • 2B variant runs on edge devices
  • Vision included on 9B+
  • Built on Gemini research

Where to download

Hugging Face: google/gemma-3-27b
Or via Ollama (ollama pull gemma-3) or LM Studio's in-app browser.

Related reading

Compare Gemma 3 with