← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Pro (16c) · 32 GB · 4bit · 2026-04-29

Performance

16k

tokens

811.5

PP tok/s

17.7

TG tok/s

20190

TTFT (ms)

21.9

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	115.9	74.0	20.0 GB	view
4k	176.8	46.5	20.4 GB	view
8k	307.3	41.2	20.8 GB	view
16k	811.5	17.7	21.9 GB	current
32k	749.0	17.3	22.6 GB	view