← Back to community benchmarks

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

M5 (10c) · 32 GB · 6bit · 2026-05-09
Performance
8k
tokens
692.5
PP tok/s
23.9
TG tok/s
11830
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 645.8 28.2 20.2 GB view
4k 709.7 26.3 20.8 GB view
8k 692.5 23.9 21.0 GB current
16k 675.8 22.8 21.5 GB view
32k 445.5 12.2 22.5 GB view
64k 283.4 7.5 23.7 GB view