← Back to community benchmarks

gemma-4-26B-A4B-it-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-06-05
Performance
4k
tokens
2,274
PP tok/s
80.3
TG tok/s
1801
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 2,274 80.3 20.7 GB current
64k 2,091 51.0 23.7 GB view
128k 1,300 33.3 28.7 GB view