← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 6bit · 2026-07-13

Performance

4k

tokens

1,793

PP tok/s

86.5

TG tok/s

2285

TTFT (ms)

28.1

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	1,793	86.5	28.1 GB	current
16k	1,468	82.7	28.3 GB	view
64k	960.2	65.3	29.4 GB	view