← Back to community benchmarks

gemma-4-e4b-it-qat-OptiQ

M5 Pro (20c) · 64 GB · 4bit · 2026-07-22
Performance
64k
tokens
2,917
PP tok/s
38.1
TG tok/s
22464
TTFT (ms)
8.6
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.5.3
macOS macOS 26.5.2
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 4,095 61.8 6.9 GB view
16k 3,782 55.0 7.2 GB view
64k 2,917 38.1 8.6 GB current