← Back to community benchmarks

gemma-4-e2b-it

M2 Max (30c) · 64 GB · 8bit · 2026-05-15
Performance
1k
tokens
3,203
PP tok/s
80.3
TG tok/s
320
TTFT (ms)
6.1
Peak mem (GB)
Hardware
Chip M2 Max (30c)
Memory 64 GB
GPU Cores 30
Software
oMLX v0.3.8
macOS macOS 26.5
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,203 80.3 6.1 GB current
4k 3,241 76.5 6.2 GB view
8k 3,186 79.1 6.2 GB view
16k 3,023 71.1 6.3 GB view
32k 2,711 63.8 6.6 GB view
64k 2,211 55.4 7.3 GB view
128k 1,651 41.7 8.8 GB view