Local LLM model page

Gemma 3n (4B)

Google Gemma for phones/tablets/laptops. Optimized for mobile and edge. 552K downloads.

Parameters
4B
Minimum RAM
6 GB
Model size
2.5 GB
Quantization
Q5_K_M

Can Gemma 3n (4B) run locally?

Gemma 3n (4B) is best suited for entry-level laptops and desktops. LocalClaw recommends Q5_K_M as the default quantization, with at least 6 GB RAM.

Search term for LM Studio or compatible runtimes: gemma-3n-e4b-it

Hugging Face repository: google/gemma-3n-E4B-it-GGUF

chatlightspeed

Strengths

  • Designed for phones/tablets/laptops
  • 128K context
  • Very efficient
  • 552K downloads

Limitations

  • Smaller than standard Gemma 3
  • Edge-optimized = some tradeoffs
  • Gemma license

Best use cases

  • Mobile AI
  • Edge deployment
  • On-device assistant
  • Quick tasks

Benchmarks

Speed: 9/10

Quality: 6/10

Coding: 5/10

Reasoning: 6/10

Technical details

Developer: Google DeepMind

License: Gemma License

Context window: 131,072 tokens

Architecture: Transformer optimized for mobile/edge

Released: 2025-06