← Back to community benchmarks

gemma-4-26b-a4b-it

M3 Max (40c) · 64 GB · 8bit · 2026-05-02

Performance

64k

tokens

842.6

PP tok/s

38.8

TG tok/s

77781

TTFT (ms)

30.0

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 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	1,027	47.5	27.5 GB	view
64k	842.6	38.8	30.0 GB	current
128k	538.2	25.1	34.2 GB	view