← Back to community benchmarks

gemma-4-E4B-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-05-29
Performance
8k
tokens
4,722
PP tok/s
95.3
TG tok/s
1735
TTFT (ms)
11.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.6
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 4,722 95.3 11.5 GB current
32k 4,936 67.0 12.5 GB view
64k 4,209 53.8 13.4 GB view
128k 3,115 40.3 15.8 GB view