← Back to community benchmarks

gemma-4-E4B-it-oQ8e

M5 (10c) · 32 GB · 8bit · 2026-05-21
Performance
16k
tokens
1,849
PP tok/s
44.1
TG tok/s
8861
TTFT (ms)
8.9
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.9
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,882 58.0 8.4 GB view
4k 1,973 54.6 8.4 GB view
8k 1,992 50.9 8.6 GB view
16k 1,849 44.1 8.9 GB current
32k 1,585 34.3 9.4 GB view
64k 1,325 23.8 10.6 GB view
128k 940.3 13.5 13.0 GB view