← Back to community benchmarks

gemma-4-e2b-it

M2 (10c) · 8 GB · 4bit · 2026-05-10
Performance
1k
tokens
1,171
PP tok/s
48.4
TG tok/s
875
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip M2 (10c)
Memory 8 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,171 48.4 3.8 GB current
4k 1,150 46.1 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
48.4 1.00×
67.0 1.38×
71.9 1.49×