Gemma 4 E2B

Gemma 4 E2B 1.5 GB

Chat 128K context · Requires Mid+ tier device

Google's 2026 on-device model — 2.3B active / 5.1B total, multimodal vision and audio

MIN TIER
Mid
SMALLEST QUANT
Q4 · 1.5 GB
CONTEXT WINDOW
128K tokens
PARAMETERS
2.3B
QUANTIZATION OPTIONS
Quant File size Quality
FP16 4.5 GB
100% 		Best quality
Q8 2.5 GB
95%
Q6 1.9 GB
85%
Q5 1.7 GB
78%
Q4 1.5 GB
70%
DEVICE COMPATIBILITY
Runs on these devices (67)
💻
MacBook Pro M4 Pro 36GB
macOS
FP16 · ~61 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M1 Max 32GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M1 Max 64GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M2 Max 32GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M2 Max 64GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M3 Max 36GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M3 Max 96GB
macOS
FP16 · ~89 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 4070) 32GB
Windows
FP16 · ~112 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 3060) 32GB
Windows
FP16 · ~80 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 4080) 32GB
Windows
FP16 · ~159 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 4090) 64GB
Windows
FP16 · ~200 tok/s · 4.5 GB
Runs great 🤖
Atom 1 64GB
Linux
FP16 · ~61 tok/s · 4.5 GB
Runs great 🤖
Atom 1 128GB
Linux
FP16 · ~61 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M4 Pro 24GB
macOS
FP16 · ~61 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M4 Pro 48GB
macOS
FP16 · ~61 tok/s · 4.5 GB
Runs great 🖥️
Mac Studio M4 Max 64GB
macOS
FP16 · ~121 tok/s · 4.5 GB
Runs great 🖥️
Mac Pro M2 Ultra 192GB
macOS
FP16 · ~178 tok/s · 4.5 GB
Runs great 🖥️
Mac Studio M1 Ultra 64GB
macOS
FP16 · ~178 tok/s · 4.5 GB
Runs great 🖥️
Mac Studio M2 Ultra 64GB
macOS
FP16 · ~178 tok/s · 4.5 GB
Runs great 🖥️
Mac Studio M3 Ultra 96GB
macOS
FP16 · ~182 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M4 Max 48GB
macOS
FP16 · ~121 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M5 Pro 24GB
macOS
FP16 · ~67 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M5 Max 48GB
macOS
FP16 · ~133 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 3080) 32GB
Windows
FP16 · ~169 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 3090) 64GB
Windows
FP16 · ~200 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 5070) 32GB
Windows
FP16 · ~149 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 5080) 32GB
Windows
FP16 · ~200 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 5090) 64GB
Windows
FP16 · ~200 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RX 7800 XT) 32GB
Windows
FP16 · ~139 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RX 7900 XTX) 64GB
Windows
FP16 · ~200 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (Arc B580) 32GB
Windows
FP16 · ~101 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (Arc A770) 32GB
Windows
FP16 · ~124 tok/s · 4.5 GB
Runs great 🤖
Atom 1 32GB
Linux
FP16 · ~46 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M1 Pro 16GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M1 Pro 32GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M2 Pro 16GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M2 Pro 32GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M2 Pro 16GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M2 Pro 32GB
macOS
FP16 · ~44 tok/s · 4.5 GB
Runs great 🖥️
Gaming PC (RTX 4060) 32GB
Windows
FP16 · ~60 tok/s · 4.5 GB
Runs well 🖥️
Gaming PC (RTX 3070) 32GB
Windows
FP16 · ~100 tok/s · 4.5 GB
Runs well 💻
MacBook Pro M3 Pro 18GB
macOS
FP16 · ~33 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M3 Pro 36GB
macOS
FP16 · ~33 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M5 16GB
macOS
FP16 · ~34 tok/s · 4.5 GB
Runs great 💻
Snapdragon X Elite Laptop 16GB
Windows
FP16 · ~30 tok/s · 4.5 GB
Runs great 💻
MacBook Air M4 16GB
macOS
FP16 · ~27 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M4 16GB
macOS
FP16 · ~27 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M4 32GB
macOS
FP16 · ~27 tok/s · 4.5 GB
Runs great 💻
MacBook Air M3 16GB
macOS
FP16 · ~22 tok/s · 4.5 GB
Runs great 💻
MacBook Air M2 16GB
macOS
FP16 · ~22 tok/s · 4.5 GB
Runs great 🎮
Steam Deck OLED 16GB
Linux
FP16 · ~20 tok/s · 4.5 GB
Runs great 💻
MacBook Air M1 16GB
macOS
FP16 · ~15 tok/s · 4.5 GB
Runs great 💻
MacBook Pro M1 16GB
macOS
FP16 · ~15 tok/s · 4.5 GB
Runs great 🖥️
Mac Mini M1 16GB
macOS
FP16 · ~15 tok/s · 4.5 GB
Runs great 💻
MacBook Air M2 8GB
macOS
FP16 · ~22 tok/s · 4.5 GB
Runs well 🖥️
Mac Mini M2 8GB
macOS
FP16 · ~22 tok/s · 4.5 GB
Runs well 💻
MacBook Air M3 8GB
macOS
FP16 · ~22 tok/s · 4.5 GB
Runs well 📱
iPad Pro M4 16GB
iOS
FP16 · ~19 tok/s · 4.5 GB
Runs well 📱
iPhone 16 Pro 8GB
iOS
Q8 · ~19 tok/s · 2.5 GB
Runs well 💻
MacBook Air M1 8GB
macOS
FP16 · ~15 tok/s · 4.5 GB
Runs well 📱
Galaxy S24 8GB
Android
Q8 · ~17 tok/s · 2.5 GB
Runs well 🖥️
Mac Mini M1 8GB
macOS
FP16 · ~15 tok/s · 4.5 GB
Runs well 📱
Pixel 9 Pro 16GB
Android
FP16 · ~11 tok/s · 4.5 GB
Runs well 📱
OnePlus 13 16GB
Android
FP16 · ~12 tok/s · 4.5 GB
Runs well 🍓
Raspberry Pi 5 8GB
Linux
FP16 · ~7 tok/s · 4.5 GB
Runs well 📱
iPhone 15 6GB
iOS
Q8 · ~12 tok/s · 2.5 GB
Tight fit 📱
Galaxy S25 Ultra 12GB
Android
FP16 · ~12 tok/s · 4.5 GB
Tight fit
RUN WITH THESE APPS
LM Studio
Beginner Free
LM Studio
Beautiful desktop app for running local AI models
Ollama
Tinkerer Free
Ollama
Lightweight CLI tool for running models in the background
Jan
Beginner Free
Jan
Open-source ChatGPT-like desktop app
LocallyAI
Beginner Free
LocallyAI
Run AI models privately on your iPhone and iPad
HOW TO RUN
Step-by-step run guides coming soon — check the apps above to get started today.