← Back to community benchmarks

Qwen3.6-35B-A3B-qx86-hi

M4 Max (40c) · 128 GB · 8bit · 2026-04-29

Performance

64k

tokens

788.8

PP tok/s

43.3

TG tok/s

83078

TTFT (ms)

42.8

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,197	83.0	37.0 GB	view
4k	1,523	79.4	37.8 GB	view
8k	1,356	76.4	38.2 GB	view
16k	1,115	68.4	38.8 GB	view
32k	1,009	60.9	40.1 GB	view
64k	788.8	43.3	42.8 GB	current