← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 128 GB · 8bit · 2026-05-10
Performance
8k
tokens
592.5
PP tok/s
31.3
TG tok/s
13826
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
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
4k 610.3 35.7 26.4 GB view
8k 592.5 31.3 26.6 GB current
16k 580.7 30.1 27.1 GB view
32k 491.4 28.3 28.0 GB view