← Back to community benchmarks

gemma-4-e4b-it-OptiQ

M4 (10c) · 24 GB · 4bit · 2026-06-05
Performance
16k
tokens
600.3
PP tok/s
23.0
TG tok/s
27294
TTFT (ms)
7.0
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 24 GB
GPU Cores 10
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 16,384
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 current
32k 555.6 20.7 7.7 GB view
64k 463.2 16.6 8.8 GB view
128k 339.5 12.5 11.0 GB view
195k 187.6 10.6 11.9 GB view