← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-07-25

Performance

32k

tokens

3,379

PP tok/s

62.8

TG tok/s

9697

TTFT (ms)

68.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.3

macOS macOS 26.5.2

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
32k	3,379	62.8	68.9 GB	current
64k	2,424	55.5	72.2 GB	view
128k	1,479	47.3	78.2 GB	view