← Back to community benchmarks

gemma-4-E4B-it-oQ4

M1 Max (24c) · 64 GB · 4bit · 2026-05-17
Performance
32k
tokens
996.5
PP tok/s
42.4
TG tok/s
32884
TTFT (ms)
6.3
Peak mem (GB)
Hardware
Chip M1 Max (24c)
Memory 64 GB
GPU Cores 24
Software
oMLX v0.3.9.dev2
macOS macOS 15.7.7
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,109 63.9 5.1 GB view
4k 1,117 61.4 5.3 GB view
8k 1,099 56.8 5.4 GB view
16k 1,073 51.3 5.6 GB view
32k 996.5 42.4 6.3 GB current
64k 875.8 28.5 7.2 GB view
128k 695.7 18.0 9.4 GB view