← Back to community benchmarks

gemma-4-e2b-it

M1 Max (24c) · 64 GB · 4bit · 2026-04-17
Performance
8k
tokens
2,129
PP tok/s
75.1
TG tok/s
3847
TTFT (ms)
3.1
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.6
macOS macOS 26.3
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,391 82.2 3.0 GB view
4k 1,919 80.7 3.1 GB view
8k 2,129 75.1 3.1 GB current