← Back to community benchmarks

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

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

Performance

64k

tokens

2,445

PP tok/s

79.1

TG tok/s

26809

TTFT (ms)

25.8

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 65,536

Performance by Context Length

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