← Back to community benchmarks

gemma-4-e2b-it

M2 (8c) · 8 GB · 4bit · 2026-04-05
Performance
1k
tokens
760.1
PP tok/s
50.9
TG tok/s
1347
TTFT (ms)
2.9
Peak mem (GB)
Hardware
Chip M2 (8c)
Memory 8 GB
GPU Cores 8
Software
oMLX v0.3.4
macOS macOS 26.2
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 760.1 50.9 2.9 GB current
4k 908.7 47.5 3.0 GB view
Batching Results
Batch Size TG tok/s Speedup
50.9 1.00×
58.4 1.15×
63.5 1.25×