← Back to community benchmarks

gemma-4-E4B-it

M3 Max (40c) · 64 GB · 8bit · 2026-05-02
Performance
32k
tokens
1,826
PP tok/s
43.4
TG tok/s
17949
TTFT (ms)
9.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,826 43.4 9.9 GB current
64k 1,487 34.9 11.0 GB view
128k 1,106 20.0 13.3 GB view