← Back to community benchmarks

gemma-4-26B-A4B-it-oQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-26

Performance

64k

tokens

572.4

PP tok/s

13.8

TG tok/s

114500

TTFT (ms)

17.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	689.0	57.4	14.4 GB	view
4k	801.4	53.8	14.8 GB	view
64k	572.4	13.8	17.8 GB	current