← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-05-14
Performance
16k
tokens
3,468
PP tok/s
80.8
TG tok/s
4725
TTFT (ms)
22.0
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 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,151 93.5 20.7 GB view
4k 3,281 89.8 21.3 GB view
8k 3,582 86.9 21.7 GB view
16k 3,468 80.8 22.0 GB current
32k 3,102 70.7 22.9 GB view
64k 2,487 56.8 24.9 GB view
Batching Results
Batch Size TG tok/s Speedup
93.5 1.00×
140.4 1.50×
196.4 2.10×