← Back to community benchmarks

gemma-4-e4b-it

M4 Pro (16c) · 24 GB · 8bit · 2026-05-31
Performance
8k
tokens
1,015
PP tok/s
59.1
TG tok/s
8068
TTFT (ms)
9.4
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 24 GB
GPU Cores 16
Software
oMLX v0.3.12
macOS macOS 26.5
Context 8,192
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 current
16k 977.6 50.5 9.7 GB view
32k 903.5 38.9 10.4 GB view
64k 783.1 26.1 11.3 GB view