← Back to community benchmarks

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

M4 Pro (16c) · 48 GB · 6bit · 2026-05-16
Performance
32k
tokens
499.4
PP tok/s
37.6
TG tok/s
65613
TTFT (ms)
22.5
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.3.8
macOS macOS 15.7.7
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
8k 588.9 46.9 20.8 GB view
16k 560.5 43.4 21.5 GB view
32k 499.4 37.6 22.5 GB current
64k 403.2 28.5 24.5 GB view