← Back to community benchmarks

gemma-4-26B-A4B-it-heretic-oQ8

M1 Max (24c) · 64 GB · 8bit · 2026-05-18

Performance

64k

tokens

278.3

PP tok/s

19.5

TG tok/s

235506

TTFT (ms)

30.0

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	319.9	39.9	25.8 GB	view
4k	344.5	38.3	26.4 GB	view
8k	352.5	36.4	26.6 GB	view
16k	343.9	33.4	27.1 GB	view
32k	321.4	28.2	28.0 GB	view
64k	278.3	19.5	30.0 GB	current