← Back to community benchmarks

gemma-4-E2B-it

M5 (10c) · 32 GB · 4bit · 2026-07-14
Performance
64k
tokens
2,411
PP tok/s
35.1
TG tok/s
27187
TTFT (ms)
5.1
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,663 55.5 3.7 GB view
4k 2,777 52.4 3.7 GB view
32k 2,817 43.4 4.3 GB view
64k 2,411 35.1 5.1 GB current
Batching Results
Batch Size TG tok/s Speedup
55.5 1.00×
107.2 1.93×