← Back to community benchmarks

gemma-4-E2B-it

M4 (10c) · 16 GB · 8bit · 2026-05-10
Performance
4k
tokens
1,856
PP tok/s
33.4
TG tok/s
2207
TTFT (ms)
6.1
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 16 GB
GPU Cores 10
Software
oMLX v0.3.9.dev1
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,721 35.8 6.0 GB view
4k 1,856 33.4 6.1 GB current
Batching Results
Batch Size TG tok/s Speedup
35.8 1.00×
69.9 1.95×
111.2 3.11×