← Back to community benchmarks

gemma-4-e2b-it

M1 Pro (16c) · 32 GB · 4bit · 2026-05-09
Performance
64k
tokens
1,123
PP tok/s
37.6
TG tok/s
58377
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip M1 Pro (16c)
Memory 32 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,114 71.4 4.0 GB view
4k 1,610 68.1 4.0 GB view
8k 1,665 63.9 4.1 GB view
16k 1,581 58.2 4.2 GB view
32k 1,416 49.5 4.5 GB view
64k 1,123 37.6 5.2 GB current
Batching Results
Batch Size TG tok/s Speedup
71.4 1.00×
140.8 1.97×
279.8 3.92×