← Back to community benchmarks

Qwen3.6-35B-A3B

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

Performance

32k

tokens

3,355

PP tok/s

78.1

TG tok/s

9766

TTFT (ms)

38.5

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 32,768

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	current
64k	2,349	68.3	41.1 GB	view