← Back to community benchmarks

gemma-4-26B-A4B-it-oQ8

M5 Max (40c) · 128 GB · 8bit · 2026-06-05
Performance
4k
tokens
3,189
PP tok/s
77.1
TG tok/s
1284
TTFT (ms)
28.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.2.dev3
macOS macOS 26.6
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,635 76.7 27.9 GB view
4k 3,189 77.1 28.6 GB current
8k 3,208 75.3 28.7 GB view
16k 3,149 71.0 29.2 GB view
32k 2,842 60.1 30.1 GB view
64k 2,306 48.5 32.1 GB view
Batching Results
Batch Size TG tok/s Speedup
76.7 1.00×
112.1 1.46×
157.2 2.05×