← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 64 GB · 8bit · 2026-04-28

Performance

1k

tokens

1,581

PP tok/s

216.4

TG tok/s

648

TTFT (ms)

36.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,581	216.4	36.1 GB	current
4k	449.7	64.7	36.2 GB	view
8k	2,140	61.1	36.5 GB	view
16k	2,034	56.7	37.1 GB	view
32k	1,739	49.2	38.5 GB	view
64k	1,241	35.2	41.2 GB	view