← Back to community benchmarks

gemma-4-E2B-it

M4 Max (40c) · 128 GB · 4bit · 2026-05-23
Performance
128k
tokens
3,356
PP tok/s
136.3
TG tok/s
39058
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 4,908 177.3 6.0 GB view
128k 3,356 136.3 8.0 GB current
195k 2,465 110.2 10.1 GB view