Skip to content

Gemma 3n E2B

by Google · gemma-3 family

2B

parameters

text-generation reasoning multilingual vision

Gemma 3n E2B is Google's ultra-compact 2B-parameter multimodal model from the Gemma 3n family, optimized for edge and on-device inference. It handles both text and vision inputs while requiring minimal memory and compute resources. As the smallest model in the Gemma 3n lineup, the E2B variant is ideal for resource-constrained environments where a lightweight model with multimodal capabilities is needed, such as mobile devices and IoT applications.

Quick Start with Ollama

ollama run e2b-q4_K_M
Resources Ollama Hugging Face Official Page
Creator Google
Parameters 2B
Architecture transformer-decoder
Context 32K tokens
Released Sep 10, 2025
License Gemma Terms of Use
Ollama gemma3n:e2b

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 1.3 GB 3.3 GB e2b-q4_K_M
Q8_0 2.2 GB 4.2 GB e2b-q8_0
F16 4 GB 6.5 GB e2b-fp16

Compatible Hardware

Q4_K_M requires 3.3 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~248 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~242 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~248 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~165 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~165 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~165 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~582 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~121 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~83 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~165 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~165 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~165 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns~291 tok/s
NVIDIA RTX A600048 GBgpuRuns~233 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns~291 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns~83 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns~121 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns~83 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns~165 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns~124 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns~83 tok/s
Mac Studio M4 Max 36GB36 GBmacRuns~165 tok/s
MacBook Pro M3 Pro 36GB36 GBmacRuns~45 tok/s
MacBook Pro M5 Max 36GB36 GBmacRuns~124 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuRuns~219 tok/s
NVIDIA GeForce RTX 509032 GBgpuRuns~543 tok/s
iMac M4 32GB32 GBmacRuns~36 tok/s
Mac mini M4 32GB32 GBmacRuns~36 tok/s
MacBook Air M4 32GB32 GBmacRuns~36 tok/s
MacBook Air M5 32GB32 GBmacRuns~36 tok/s
MacBook Pro M5 32GB32 GBmacRuns~36 tok/s
AMD Radeon RX 7900 XTX24 GBgpuRuns~291 tok/s
NVIDIA GeForce RTX 3090 Ti24 GBgpuRuns~305 tok/s
NVIDIA GeForce RTX 309024 GBgpuRuns~284 tok/s
NVIDIA GeForce RTX 409024 GBgpuRuns~305 tok/s
NVIDIA RTX A500024 GBgpuRuns~233 tok/s
iMac M3 24GB24 GBmacRuns~30 tok/s
Mac mini M2 24GB24 GBmacRuns~30 tok/s
Mac mini M4 Pro 24GB24 GBmacRuns~83 tok/s
MacBook Air M2 24GB24 GBmacRuns~30 tok/s
MacBook Air M4 24GB24 GBmacRuns~36 tok/s
MacBook Air M5 24GB24 GBmacRuns~36 tok/s
MacBook Pro M4 Pro 24GB24 GBmacRuns~83 tok/s
MacBook Pro M5 24GB24 GBmacRuns~36 tok/s
MacBook Pro M5 Pro 24GB24 GBmacRuns~83 tok/s
AMD Radeon RX 7900 XT20 GBgpuRuns~242 tok/s
NVIDIA RTX 4000 Ada Generation20 GBgpuRuns~109 tok/s
MacBook Pro M3 Pro 18GB18 GBmacRuns~45 tok/s
AMD Radeon RX 6800 XT16 GBgpuRuns~155 tok/s
AMD Radeon RX 6900 XT16 GBgpuRuns~155 tok/s
AMD Radeon RX 7800 XT16 GBgpuRuns~189 tok/s
AMD Radeon RX 9060 XT 16GB16 GBgpuRuns~163 tok/s
AMD Radeon RX 9070 XT16 GBgpuRuns~197 tok/s
AMD Radeon RX 907016 GBgpuRuns~163 tok/s
Intel Arc A77016 GBgpuRuns~170 tok/s
NVIDIA GeForce RTX 4060 Ti 16GB16 GBgpuRuns~87 tok/s
NVIDIA GeForce RTX 4070 Ti Super16 GBgpuRuns~204 tok/s
NVIDIA GeForce RTX 4080 Super16 GBgpuRuns~223 tok/s
NVIDIA GeForce RTX 408016 GBgpuRuns~217 tok/s
NVIDIA GeForce RTX 5060 Ti 16GB16 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 5070 Ti16 GBgpuRuns~272 tok/s
NVIDIA GeForce RTX 508016 GBgpuRuns~291 tok/s
NVIDIA RTX A400016 GBgpuRuns~136 tok/s
iMac M1 16GB16 GBmacRuns~21 tok/s
iMac M4 16GB16 GBmacRuns~36 tok/s
Mac mini M1 16GB16 GBmacRuns~21 tok/s
Mac mini M4 16GB16 GBmacRuns~36 tok/s
MacBook Air M2 16GB16 GBmacRuns~30 tok/s
MacBook Air M3 16GB16 GBmacRuns~30 tok/s
MacBook Air M4 16GB16 GBmacRuns~36 tok/s
MacBook Air M5 16GB16 GBmacRuns~36 tok/s
MacBook Pro M1 16GB16 GBmacRuns~21 tok/s
MacBook Pro M2 Pro 16GB16 GBmacRuns~61 tok/s
MacBook Pro M5 16GB16 GBmacRuns~36 tok/s
AMD Radeon RX 6700 XT12 GBgpuRuns~116 tok/s
AMD Radeon RX 7700 XT12 GBgpuRuns~131 tok/s
Intel Arc B58012 GBgpuRuns~138 tok/s
NVIDIA GeForce RTX 3060 12GB12 GBgpuRuns~109 tok/s
NVIDIA GeForce RTX 3080 12GB12 GBgpuRuns~276 tok/s
NVIDIA GeForce RTX 4070 Super12 GBgpuRuns~153 tok/s
NVIDIA GeForce RTX 4070 Ti12 GBgpuRuns~153 tok/s
NVIDIA GeForce RTX 407012 GBgpuRuns~153 tok/s
NVIDIA GeForce RTX 507012 GBgpuRuns~204 tok/s
NVIDIA GeForce GTX 1080 Ti11 GBgpuRuns~147 tok/s
NVIDIA GeForce RTX 2080 Ti11 GBgpuRuns~187 tok/s
Intel Arc B57010 GBgpuRuns~115 tok/s
NVIDIA GeForce RTX 3080 10GB10 GBgpuRuns~230 tok/s
AMD Radeon RX 6600 XT8 GBgpuRuns~78 tok/s
AMD Radeon RX 76008 GBgpuRuns~87 tok/s
Intel Arc A7508 GBgpuRuns~155 tok/s
AMD Radeon RX 9060 XT 8GB8 GBgpuRuns~82 tok/s
NVIDIA GeForce GTX 10708 GBgpuRuns~78 tok/s
NVIDIA GeForce RTX 2060 Super8 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 2070 Super8 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 2080 Super8 GBgpuRuns~150 tok/s
NVIDIA GeForce RTX 30508 GBgpuRuns~68 tok/s
NVIDIA GeForce RTX 3060 Ti8 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 30708 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 40608 GBgpuRuns~82 tok/s
NVIDIA GeForce RTX 4060 Ti 8GB8 GBgpuRuns~87 tok/s
NVIDIA GeForce RTX 50508 GBgpuRuns~68 tok/s
NVIDIA GeForce RTX 5060 Ti 8GB8 GBgpuRuns~136 tok/s
NVIDIA GeForce RTX 50608 GBgpuRuns~102 tok/s
MacBook Air M1 8GB8 GBmacRuns~21 tok/s
MacBook Air M2 8GB8 GBmacRuns~30 tok/s
NVIDIA GeForce GTX 1660 Super6 GBgpuRuns~102 tok/s
NVIDIA GeForce RTX 20606 GBgpuRuns~102 tok/s