← Back to community benchmarks

gemma-4-E2B-it-oQ8e

M5 Max (40c) · 128 GB · 8bit · 2026-07-17

Performance

64k

tokens

4,958

PP tok/s

101.7

TG tok/s

13218

TTFT (ms)

6.5

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536