← Back to community benchmarks

Qwen3.6-35B-A3B-oQ8-mtp

M5 Max (40c) · 128 GB · 8bit · 2026-06-07

Performance

16k

tokens

2,014

PP tok/s

49.3

TG tok/s

8135

TTFT (ms)

38.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.4.2rc1

macOS macOS 26.5.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	2,517	50.2	37.0 GB	view
16k	2,014	49.3	38.0 GB	current
64k	1,351	37.1	42.4 GB	view