← Back to community benchmarks

gemma-4-e4b-it

M3 Pro (14c) · 36 GB · 4bit · 2026-05-01
Performance
32k
tokens
686.9
PP tok/s
29.1
TG tok/s
47705
TTFT (ms)
6.4
Peak mem (GB)
Hardware
Chip M3 Pro (14c)
Memory 36 GB
GPU Cores 14
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 686.9 29.1 6.4 GB current
64k 570.2 22.6 7.1 GB view