← Back to community benchmarks

gemma-4-26B-A4B-it

M5 Pro (20c) · 64 GB · 6bit · 2026-05-12
Performance
1k
tokens
1,434
PP tok/s
59.2
TG tok/s
714
TTFT (ms)
20.0
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.3.9.dev1
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,434 59.2 20.0 GB current
4k 1,871 57.5 20.7 GB view
32k 1,742 43.1 22.0 GB view
64k 1,363 32.8 24.3 GB view
128k 953.1 22.7 28.4 GB view