← Back to community benchmarks

gemma-4-e4b-it-OptiQ

M4 (10c) · 24 GB · 4bit · 2026-06-05
Performance
64k
tokens
463.2
PP tok/s
16.6
TG tok/s
141478
TTFT (ms)
8.8
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 614.9 24.9 6.7 GB view
16k 600.3 23.0 7.0 GB view
32k 555.6 20.7 7.7 GB view
64k 463.2 16.6 8.8 GB current
128k 339.5 12.5 11.0 GB view
195k 187.6 10.6 11.9 GB view