← Back to community benchmarks

gemma-4-E4B-RotorQuant

M5 (10c) · 32 GB · 8bit · 2026-05-25
Performance
64k
tokens
581.5
PP tok/s
8.6
TG tok/s
112705
TTFT (ms)
10.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.10
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 965.6 15.6 9.2 GB view
32k 855.2 11.0 9.8 GB view
64k 581.5 8.6 10.9 GB current