← Back to community benchmarks

gemma-4-e4b-it

M2 Pro (16c) · 16 GB · 4bit · 2026-04-03
Performance
16k
tokens
500.6
PP tok/s
21.1
TG tok/s
32727
TTFT (ms)
7.2
Peak mem (GB)
Hardware
Chip M2 Pro (16c)
Memory 16 GB
GPU Cores 16
Software
oMLX v0.3.2
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 513.5 29.6 6.9 GB view
4k 518.9 28.5 7.0 GB view
8k 513.1 26.3 7.1 GB view
16k 500.6 21.1 7.2 GB current
32k 475.5 16.8 7.8 GB view
64k 431.9 9.8 8.4 GB view