← Back to community benchmarks

gemma-4-26b-a4b-it

M5 Max (40c) · 128 GB · 8bit · 2026-05-23
Performance
32k
tokens
3,045
PP tok/s
64.9
TG tok/s
10763
TTFT (ms)
27.5
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 3,045 64.9 27.5 GB current
64k 2,166 50.6 30.0 GB view