← Back to community benchmarks

gemma-4-e4b-it

M4 Pro (16c) · 24 GB · 8bit · 2026-05-31
Performance
16k
tokens
977.6
PP tok/s
50.5
TG tok/s
16760
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.12
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,007 71.3 9.1 GB view
4k 1,005 66.0 9.2 GB view
8k 1,015 59.1 9.4 GB view
16k 977.6 50.5 9.7 GB current
32k 903.5 38.9 10.4 GB view
64k 783.1 26.1 11.3 GB view