← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-06-04
Performance
16k
tokens
3,124
PP tok/s
75.4
TG tok/s
5244
TTFT (ms)
21.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.1
macOS macOS 26.5.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,104 86.9 20.3 GB view
4k 2,959 84.4 20.9 GB view
8k 3,240 79.3 21.1 GB view
16k 3,124 75.4 21.5 GB current
Batching Results
Batch Size TG tok/s Speedup
86.9 1.00×
132.2 1.52×
178.6 2.06×