← Back to community benchmarks

gemma-4-E2B-it

M1 Max (24c) · 64 GB · 4bit · 2026-05-25
Performance
32k
tokens
1,130
PP tok/s
29.7
TG tok/s
29002
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,276 41.6 4.7 GB view
4k 1,155 48.5 4.7 GB view
8k 1,142 46.0 4.8 GB view
16k 1,201 45.1 4.9 GB view
32k 1,130 29.7 5.3 GB current
64k 892.4 21.1 6.0 GB view