← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4-mtp

M5 Max (40c) · 128 GB · 4bit · 2026-07-19

Performance

128k

tokens

1,021

PP tok/s

49.8

TG tok/s

128367

TTFT (ms)

31.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.2.dev1

macOS macOS 26.4

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	2,445	79.1	25.8 GB	view
128k	1,021	49.8	31.2 GB	current
195k	670.5	38.9	36.8 GB	view