← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-07-20

Performance

64k

tokens

2,349

PP tok/s

68.3

TG tok/s

27903

TTFT (ms)

41.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	3,952	83.8	37.2 GB	view
32k	3,355	78.1	38.5 GB	view
64k	2,349	68.3	41.1 GB	current