← 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.Homepage: https://ai.google.dev/gemma
Related reading
Best Open Source LLMs 2026: Honest Picks by Use Case
Which open-source LLM should you actually run in 2026? Honest picks by use case — frontier reasoning, coding, RAG, edge devices, multilingual.
Open Source LLM Licenses Explained: Llama vs Apache vs Gemma vs MIT
Can you use Llama in a commercial product? What does the Gemma license actually restrict? A plain-English breakdown of every major open LLM license.
Running an LLM on Your Laptop in 2026: M-Series, Quantization, and What Actually Works
Step-by-step: pick a quantization, install Ollama or LM Studio, run a 7B-14B model on a MacBook or 16GB GPU, and not lose your sanity.
Small LLMs on Edge Devices: What Runs on Phones, Pis, and Browsers in 2026
Gemma 2B runs on a Pi 5. Phi-4 runs in a browser via WebGPU. Phones run Llama 3B. A practical guide to LLMs on tiny hardware.