← Back to community benchmarks

gemma-4-e2b-it

M4 Max (40c) · 64 GB · 4bit · 2026-05-19
Performance
64k
tokens
4,816
PP tok/s
109.3
TG tok/s
13607
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 65,536