← Back to community benchmarks

gemma-4-E4B-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-06-05
Performance
128k
tokens
2,700
PP tok/s
47.0
TG tok/s
48543
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.2.dev3
macOS macOS 26.6
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 3,968 108.3 11.2 GB view
8k 4,741 101.2 11.5 GB view
16k 4,209 96.0 11.8 GB view
32k 4,275 88.4 12.5 GB view
64k 3,648 74.5 13.4 GB view
128k 2,700 47.0 15.8 GB current
Batching Results
Batch Size TG tok/s Speedup
108.3 1.00×
66.6 0.61×
144.7 1.34×