← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-05-29
Performance
64k
tokens
2,404
PP tok/s
53.7
TG tok/s
27257
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.12
macOS macOS 26.6
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,128 89.7 22.4 GB view
4k 3,071 87.7 23.0 GB view
8k 3,355 84.7 23.2 GB view
16k 3,219 76.5 23.7 GB view
32k 2,924 65.8 24.6 GB view
64k 2,404 53.7 26.6 GB current
128k 1,674 37.5 30.8 GB view
Batching Results
Batch Size TG tok/s Speedup
89.7 1.00×
130.4 1.45×
187.5 2.09×