← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4e-mtp

M4 Max (40c) · 64 GB · 4bit · 2026-07-14

Performance

4k

tokens

1,674

PP tok/s

91.8

TG tok/s

2446

TTFT (ms)

20.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,674	91.8	20.6 GB	current
16k	1,382	88.9	21.0 GB	view
64k	860.7	69.1	22.0 GB	view