Run Gemma 4 E2B on M4 Pro

Yes — Gemma 4 E2B (2.3B) runs at 95 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.2s. Google's ultra-compact 2.3B MoE model with multimodal and audio support.

Speed
95
tok/s
First Token
0.2
seconds
RAM Needed
24
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Gemma 4 E2B on M4 Pro using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

MetricValue
Tokens per second95 tok/s
Time to first token0.2s
QuantizationQ4_K_M
Minimum RAM24 GB
Recommended engineOllama
Parameters2.3B
Benchmark date2026-04

Q4_K_M 2.3B Ollama M4 Pro

Setup Guide: Run Gemma 4 E2B on M4 Pro

The recommended engine for Gemma 4 E2B on M4 Pro is Ollama. Install Ollama, then pull the model:

ollama run gemma4:e2b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 158 tok/s 0.1s 128 GB MLX
M3 82 tok/s 0.3s 16 GB Ollama
M1 58 tok/s 0.5s 8 GB Ollama

System Requirements

To run Gemma 4 E2B on M4 Pro you need:

Compare More Models

See how Gemma 4 E2B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard