← Back to community benchmarks

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

M5 Max (40c) · 128 GB · 6bit · 2026-05-19
Performance
4k
tokens
3,179
PP tok/s
89.3
TG tok/s
1289
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9rc1
macOS macOS 26.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,151 92.6 20.7 GB view
4k 3,179 89.3 21.3 GB current
8k 3,492 85.2 21.8 GB view
16k 3,422 80.2 22.0 GB view
32k 3,082 70.5 22.9 GB view
64k 2,470 56.5 24.9 GB view