← Back to community benchmarks

local--Agents-A1

M5 Max (40c) · 128 GB · 4bit · 2026-07-01

Performance

32k

tokens

1,806

PP tok/s

104.2

TG tok/s

18149

TTFT (ms)

20.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.5.dev1

macOS macOS 26.5.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	3,708	119.8	19.2 GB	view
4k	4,379	122.1	20.0 GB	view
8k	4,134	116.7	20.4 GB	view
16k	2,429	110.2	20.3 GB	view
32k	1,806	104.2	20.6 GB	current
64k	1,101	79.5	21.2 GB	view
128k	650.2	58.8	22.4 GB	view