← Back to community benchmarks

gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI

M2 Max (30c) · 32 GB · 4bit · 2026-04-19

Performance

32k

tokens

1,244

PP tok/s

23.3

TG tok/s

26347

TTFT (ms)

10.6

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	1,324	28.2	10.1 GB	view
32k	1,244	23.3	10.6 GB	current