← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 4bit · 2026-04-26

Performance

8k

tokens

2,502

PP tok/s

116.6

TG tok/s

3274

TTFT (ms)

19.4

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,893	251.5	19.6 GB	view
4k	1,345	124.9	19.0 GB	view
8k	2,502	116.6	19.4 GB	current
16k	2,559	109.5	20.0 GB	view