← Back to community benchmarks

gemma-4-E4B-it-oQ4

M5 (10c) · 32 GB · 4bit · 2026-05-09
Performance
8k
tokens
1,645
PP tok/s
34.9
TG tok/s
4980
TTFT (ms)
5.2
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,275 36.9 5.0 GB view
4k 1,589 36.7 5.0 GB view
8k 1,645 34.9 5.2 GB current
16k 1,500 30.4 5.3 GB view
32k 1,313 25.5 5.8 GB view
64k 1,096 18.3 6.6 GB view
128k 615.0 7.8 8.4 GB view