← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Max (40c) · 64 GB · 4bit · 2026-04-29

Performance

16k

tokens

1,499

PP tok/s

80.6

TG tok/s

10930

TTFT (ms)

21.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,613	96.4	20.7 GB	view
8k	1,642	90.2	21.1 GB	view
16k	1,499	80.6	21.7 GB	current