← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

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

Performance

16k

tokens

1,382

PP tok/s

79.8

TG tok/s

11856

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	1,618	94.8	20.7 GB	view
8k	1,608	90.0	21.1 GB	view
16k	1,382	79.8	21.7 GB	current