← Back to community benchmarks

gemma-4-26B-A4B-it-unsloth

M5 Max (40c) · 128 GB · bf16 · 2026-05-18

Performance

1k

tokens

1,817

PP tok/s

56.4

TG tok/s

564

TTFT (ms)

47.8

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,817	56.4	47.8 GB	current
4k	2,936	49.5	48.5 GB	view
64k	2,277	39.6	51.2 GB	view