← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-26

Performance

8k

tokens

2,153

PP tok/s

171.8

TG tok/s

3806

TTFT (ms)

68.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,300	186.6	67.0 GB	view
4k	2,701	170.7	68.0 GB	view
8k	2,153	171.8	68.2 GB	current
16k	1,466	155.4	68.9 GB	view