← Back to community benchmarks

unsloth--Qwen3.6-35B-A3B-UD

M5 Pro (20c) · 64 GB · 4bit · 2026-07-18

Performance

1k

tokens

2,004

PP tok/s

73.7

TG tok/s

511

TTFT (ms)

20.4

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,004	73.7	20.4 GB	current
4k	2,430	72.3	21.2 GB	view
8k	2,363	69.5	21.5 GB	view
16k	1,501	65.9	21.7 GB	view
32k	1,011	59.7	22.4 GB	view
64k	624.1	49.9	22.7 GB	view