← Back to community benchmarks

gemma-4-E4B-it-oQ4

M5 (10c) · 32 GB · 4bit · 2026-06-05
Performance
16k
tokens
1,697
PP tok/s
30.9
TG tok/s
9656
TTFT (ms)
5.5
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 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
1k 1,311 37.4 5.0 GB view
4k 1,656 36.5 5.0 GB view
8k 1,815 34.2 5.2 GB view
16k 1,697 30.9 5.5 GB current
32k 1,503 26.1 6.0 GB view
64k 1,220 19.4 7.1 GB view