← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Max (40c) · 64 GB · 8bit · 2026-05-02
Performance
128k
tokens
611.7
PP tok/s
28.1
TG tok/s
214280
TTFT (ms)
34.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 131,072
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
32k 1,010 47.7 27.5 GB view
64k 796.7 39.0 30.0 GB view
128k 611.7 28.1 34.2 GB current