← Back to community benchmarks

gemma-4-26B-A4B-it

M4 Max (40c) · 64 GB · 8bit · 2026-05-24
Performance
64k
tokens
997.5
PP tok/s
48.8
TG tok/s
65702
TTFT (ms)
30.0
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.9
macOS macOS 26.5
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 1,276 76.3 26.2 GB view
32k 1,221 61.3 27.8 GB view
64k 997.5 48.8 30.0 GB current