← Back to community benchmarks

gemma-4-E4B-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-05-29
Performance
64k
tokens
4,238
PP tok/s
63.5
TG tok/s
15466
TTFT (ms)
13.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.6
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 4,962 86.7 12.5 GB view
64k 4,238 63.5 13.4 GB current
128k 3,133 41.7 15.8 GB view