← Back to community benchmarks

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

M5 Pro (20c) · 64 GB · 4bit · 2026-07-21

Performance

16k

tokens

1,988

PP tok/s

66.2

TG tok/s

8241

TTFT (ms)

22.2

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.4.4

macOS macOS 26.5.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,671	73.4	20.4 GB	view
4k	2,233	71.8	21.2 GB	view
8k	2,148	69.9	21.5 GB	view
16k	1,988	66.2	22.2 GB	current
32k	1,664	59.8	23.5 GB	view
64k	1,198	49.7	26.2 GB	view