← Back to community benchmarks

gemma-4-E4B-it

M4 Pro (16c) · 48 GB · 4bit · 2026-05-09
Performance
8k
tokens
1,017
PP tok/s
44.5
TG tok/s
8055
TTFT (ms)
7.3
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,011 47.2 7.0 GB view
4k 1,014 46.0 7.1 GB view
8k 1,017 44.5 7.3 GB current
16k 979.6 41.5 7.5 GB view
32k 910.6 36.9 8.2 GB view
64k 797.6 30.2 8.6 GB view
128k 636.9 21.9 10.3 GB view