← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-05-14
Performance
32k
tokens
3,062
PP tok/s
71.0
TG tok/s
10701
TTFT (ms)
22.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9.dev2
macOS macOS 26.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,118 93.6 20.7 GB view
4k 3,274 90.3 21.3 GB view
8k 3,564 86.4 21.7 GB view
16k 3,460 79.6 22.0 GB view
32k 3,062 71.0 22.9 GB current
64k 2,461 56.9 24.9 GB view
Batching Results
Batch Size TG tok/s Speedup
93.6 1.00×
136.2 1.46×
191.6 2.05×