Skip to content

Gemma 4 E2B

by Google · gemma-4 family

2B

parameters

text-generation reasoning multilingual vision

Gemma 4 E2B is Google's smallest Gemma 4 model with 2.3B effective parameters, designed for edge and mobile deployment. Despite its compact size, it supports vision input and 140+ languages with a 128K context window. At Q4 it needs just 4 GB of VRAM, making it one of the most capable models you can run on virtually any hardware — including phones and Raspberry Pi devices.

Quick Start with Ollama

ollama run e2b-it-q4_K_M
Resources Ollama Hugging Face Official Page
Creator Google
Parameters 2B
Architecture transformer-decoder
Context 128K tokens
Released Apr 2, 2026
License Apache 2.0
Ollama gemma4:e2b

Quantization Options

Format File Size VRAM Required Quality Ollama Tag
Q4_K_M rec 7.2 GB 4 GB e2b-it-q4_K_M
Q8_0 8.1 GB 6 GB e2b-it-q8_0

Compatible Hardware

Q4_K_M requires 4 GB VRAM

Compatible Hardware

HardwareVRAMTypeFitEst. Speed
Mac Studio M4 Ultra 512GB512 GBmacRuns~205 tok/s
Mac Pro M2 Ultra 192GB192 GBmacRuns~200 tok/s
Mac Studio M4 Ultra 192GB192 GBmacRuns~205 tok/s
Mac Studio M4 Max 128GB128 GBmacRuns~137 tok/s
MacBook Pro M4 Max 128GB128 GBmacRuns~137 tok/s
MacBook Pro M5 Max 128GB128 GBmacRuns~137 tok/s
NVIDIA RTX PRO 6000 Blackwell96 GBgpuRuns~480 tok/s
MacBook Pro M3 Max 96GB96 GBmacRuns~100 tok/s
Mac mini M4 Pro 64GB64 GBmacRuns~68 tok/s
Mac Studio M4 Max 64GB64 GBmacRuns~137 tok/s
MacBook Pro M4 Max 64GB64 GBmacRuns~137 tok/s
MacBook Pro M5 Max 64GB64 GBmacRuns~137 tok/s
NVIDIA RTX 6000 Ada Generation48 GBgpuRuns~240 tok/s
NVIDIA RTX A600048 GBgpuRuns~192 tok/s
NVIDIA RTX PRO 5000 Blackwell48 GBgpuRuns~240 tok/s
Mac mini M4 Pro 48GB48 GBmacRuns~68 tok/s
MacBook Pro M3 Max 48GB48 GBmacRuns~100 tok/s
MacBook Pro M4 Max 48GB48 GBmacRuns~137 tok/s
MacBook Pro M4 Pro 48GB48 GBmacRuns~68 tok/s
MacBook Pro M5 Max 48GB48 GBmacRuns~103 tok/s
MacBook Pro M5 Pro 48GB48 GBmacRuns~68 tok/s
Mac Studio M4 Max 36GB36 GBmacRuns~137 tok/s
MacBook Pro M3 Pro 36GB36 GBmacRuns~38 tok/s
MacBook Pro M5 Max 36GB36 GBmacRuns~103 tok/s
NVIDIA RTX 5000 Ada Generation32 GBgpuRuns~181 tok/s
NVIDIA GeForce RTX 509032 GBgpuRuns~448 tok/s
iMac M4 32GB32 GBmacRuns~30 tok/s
Mac mini M4 32GB32 GBmacRuns~30 tok/s
MacBook Air M4 32GB32 GBmacRuns~30 tok/s
MacBook Air M5 32GB32 GBmacRuns~30 tok/s
MacBook Pro M5 32GB32 GBmacRuns~30 tok/s
AMD Radeon RX 7900 XTX24 GBgpuRuns~240 tok/s
NVIDIA GeForce RTX 309024 GBgpuRuns~234 tok/s
NVIDIA GeForce RTX 3090 Ti24 GBgpuRuns~252 tok/s
NVIDIA GeForce RTX 409024 GBgpuRuns~252 tok/s
NVIDIA RTX A500024 GBgpuRuns~192 tok/s
iMac M3 24GB24 GBmacRuns~25 tok/s
Mac mini M2 24GB24 GBmacRuns~25 tok/s
Mac mini M4 Pro 24GB24 GBmacRuns~68 tok/s
MacBook Air M2 24GB24 GBmacRuns~25 tok/s
MacBook Air M4 24GB24 GBmacRuns~30 tok/s
MacBook Air M5 24GB24 GBmacRuns~30 tok/s
MacBook Pro M4 Pro 24GB24 GBmacRuns~68 tok/s
MacBook Pro M5 24GB24 GBmacRuns~30 tok/s
MacBook Pro M5 Pro 24GB24 GBmacRuns~68 tok/s
AMD Radeon RX 7900 XT20 GBgpuRuns~200 tok/s
NVIDIA RTX 4000 Ada Generation20 GBgpuRuns~90 tok/s
MacBook Pro M3 Pro 18GB18 GBmacRuns~38 tok/s
AMD Radeon RX 6900 XT16 GBgpuRuns~128 tok/s
AMD Radeon RX 6800 XT16 GBgpuRuns~128 tok/s
AMD Radeon RX 7800 XT16 GBgpuRuns~156 tok/s
AMD Radeon RX 9060 XT 16GB16 GBgpuRuns~135 tok/s
AMD Radeon RX 9070 XT16 GBgpuRuns~163 tok/s
AMD Radeon RX 907016 GBgpuRuns~135 tok/s
Intel Arc A77016 GBgpuRuns~140 tok/s
NVIDIA GeForce RTX 4060 Ti 16GB16 GBgpuRuns~72 tok/s
NVIDIA GeForce RTX 4070 Ti Super16 GBgpuRuns~168 tok/s
NVIDIA GeForce RTX 4080 Super16 GBgpuRuns~184 tok/s
NVIDIA GeForce RTX 408016 GBgpuRuns~179 tok/s
NVIDIA GeForce RTX 5060 Ti 16GB16 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 5070 Ti16 GBgpuRuns~224 tok/s
NVIDIA GeForce RTX 508016 GBgpuRuns~240 tok/s
NVIDIA RTX A400016 GBgpuRuns~112 tok/s
iMac M1 16GB16 GBmacRuns~17 tok/s
iMac M4 16GB16 GBmacRuns~30 tok/s
Mac mini M1 16GB16 GBmacRuns~17 tok/s
Mac mini M4 16GB16 GBmacRuns~30 tok/s
MacBook Air M2 16GB16 GBmacRuns~25 tok/s
MacBook Air M3 16GB16 GBmacRuns~25 tok/s
MacBook Air M4 16GB16 GBmacRuns~30 tok/s
MacBook Air M5 16GB16 GBmacRuns~30 tok/s
MacBook Pro M1 16GB16 GBmacRuns~17 tok/s
MacBook Pro M2 Pro 16GB16 GBmacRuns~50 tok/s
MacBook Pro M5 16GB16 GBmacRuns~30 tok/s
AMD Radeon RX 6700 XT12 GBgpuRuns~96 tok/s
AMD Radeon RX 7700 XT12 GBgpuRuns~108 tok/s
Intel Arc B58012 GBgpuRuns~114 tok/s
NVIDIA GeForce RTX 3060 12GB12 GBgpuRuns~90 tok/s
NVIDIA GeForce RTX 3080 12GB12 GBgpuRuns~228 tok/s
NVIDIA GeForce RTX 4070 Super12 GBgpuRuns~126 tok/s
NVIDIA GeForce RTX 4070 Ti12 GBgpuRuns~126 tok/s
NVIDIA GeForce RTX 407012 GBgpuRuns~126 tok/s
NVIDIA GeForce RTX 507012 GBgpuRuns~168 tok/s
NVIDIA GeForce GTX 1080 Ti11 GBgpuRuns~121 tok/s
NVIDIA GeForce RTX 2080 Ti11 GBgpuRuns~154 tok/s
Intel Arc B57010 GBgpuRuns~95 tok/s
NVIDIA GeForce RTX 3080 10GB10 GBgpuRuns~190 tok/s
AMD Radeon RX 6600 XT8 GBgpuRuns~64 tok/s
AMD Radeon RX 76008 GBgpuRuns~72 tok/s
AMD Radeon RX 9060 XT 8GB8 GBgpuRuns~67 tok/s
Intel Arc A7508 GBgpuRuns~128 tok/s
NVIDIA GeForce GTX 10708 GBgpuRuns~64 tok/s
NVIDIA GeForce RTX 2060 Super8 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 2070 Super8 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 2080 Super8 GBgpuRuns~124 tok/s
NVIDIA GeForce RTX 30508 GBgpuRuns~56 tok/s
NVIDIA GeForce RTX 30708 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 3060 Ti8 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 4060 Ti 8GB8 GBgpuRuns~72 tok/s
NVIDIA GeForce RTX 40608 GBgpuRuns~68 tok/s
NVIDIA GeForce RTX 50508 GBgpuRuns~56 tok/s
NVIDIA GeForce RTX 5060 Ti 8GB8 GBgpuRuns~112 tok/s
NVIDIA GeForce RTX 50608 GBgpuRuns~84 tok/s
MacBook Air M1 8GB8 GBmacRuns~17 tok/s
MacBook Air M2 8GB8 GBmacRuns~25 tok/s
NVIDIA GeForce GTX 1660 Super6 GBgpuRuns~84 tok/s
NVIDIA GeForce RTX 20606 GBgpuRuns~84 tok/s