← Back to community benchmarks

gemma-4-E2B-it

M3 Max (40c) · 48 GB · 8bit · 2026-05-19
Performance
64k
tokens
3,972
PP tok/s
69.7
TG tok/s
16500
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 65,536