← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 4bit · 2026-05-28
Performance
128k
tokens
1,738
PP tok/s
40.1
TG tok/s
75400
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
64k 2,580 59.3 17.7 GB view
128k 1,738 40.1 21.2 GB current
195k 1,293 29.1 24.9 GB view