← Back to community benchmarks

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

M2 Max (38c) · 64 GB · 6bit · 2026-05-15
Performance
8k
tokens
1,077
PP tok/s
50.1
TG tok/s
7605
TTFT (ms)
21.1
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.3.9.dev2-memtest
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 869.3 53.3 20.3 GB view
4k 1,024 52.0 20.7 GB view
8k 1,077 50.1 21.1 GB current
16k 1,027 46.7 21.5 GB view
32k 927.8 41.8 22.5 GB view
64k 773.6 34.2 24.5 GB view
128k 543.0 26.0 28.7 GB view
195k 400.8 18.7 33.7 GB view
Batching Results
Batch Size TG tok/s Speedup
53.3 1.00×
81.2 1.52×
105.8 1.98×