← Back to community benchmarks

gm4-26b-a4b-ih

M5 Max (40c) · 64 GB · 4bit · 2026-05-01

Performance

1k

tokens

2,298

PP tok/s

111.2

TG tok/s

446

TTFT (ms)

14.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 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	2,298	111.2	14.3 GB	current
4k	2,129	105.1	14.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	111.2	1.00×
2×	157.8	1.42×
4×	220.6	1.98×