← Back to community benchmarks

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

M3 Max (40c) · 128 GB · 6bit · 2026-04-16
Performance
8k
tokens
1,182
PP tok/s
55.6
TG tok/s
6931
TTFT (ms)
20.9
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 991.9 68.0 20.2 GB view
4k 1,127 64.6 20.7 GB view
8k 1,182 55.6 20.9 GB current
16k 1,085 39.6 21.2 GB view
32k 1,035 25.6 22.1 GB view
Batching Results
Batch Size TG tok/s Speedup
68.0 1.00×
104.7 1.54×
137.5 2.02×
164.6 2.42×