← Back to community benchmarks

gemma-4-e4b-it

M2 Pro (16c) · 16 GB · 4bit · 2026-04-03
Performance
8k
tokens
512.5
PP tok/s
25.7
TG tok/s
15984
TTFT (ms)
7.1
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
8k 512.5 25.7 7.1 GB current
16k 500.5 21.7 7.2 GB view
32k 475.2 16.2 7.8 GB view
64k 431.5 9.8 8.4 GB view