Run Gemma 4 E2B on M5 Max

Yes — Gemma 4 E2B (2.3B) runs at 158 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.1s. Google's ultra-compact 2.3B MoE model with multimodal and audio support.

Speed

158

tok/s

First Token

0.1

seconds

RAM Needed

128

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Gemma 4 E2B on M5 Max using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

Metric	Value
Tokens per second	158 tok/s
Time to first token	0.1s
Quantization	Q4_K_M
Minimum RAM	128 GB
Recommended engine	MLX
Parameters	2.3B
Benchmark date	2026-04

Q4_K_M 2.3B MLX M5 Max

Setup Guide: Run Gemma 4 E2B on M5 Max

The recommended engine for Gemma 4 E2B on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/gemma-4-e2b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run gemma4:e2b

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M4 Pro	95 tok/s	0.2s	24 GB	Ollama
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 M5 Max you need:

• Mac with M5 Max chip (or newer)
• 128 GB unified memory minimum
• macOS 13 Ventura or later
• ~108-128 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

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

Open Compare Tool Full Leaderboard