← Back to community benchmarks

gemma-4-e4b-it

M2 Pro (16c) · 16 GB · 8bit · 2026-04-03
Performance
8k
tokens
461.6
PP tok/s
21.5
TG tok/s
17747
TTFT (ms)
9.1
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 467.8 23.8 8.9 GB view
4k 466.6 22.8 9.0 GB view
8k 461.6 21.5 9.1 GB current
16k 452.9 18.3 9.3 GB view
32k 403.4 1.2 9.8 GB view
64k 426.9 10.9 10.5 GB view