← Back to community benchmarks

Qwen3.6-35B-A3B-oQ3

M1 Max (32c) · 64 GB · 3bit · 2026-04-19

Performance

32k

tokens

796.6

PP tok/s

35.6

TG tok/s

41135

TTFT (ms)

19.1

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.2

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	768.7	66.3	16.1 GB	view
4k	957.9	65.3	16.8 GB	view
8k	959.4	60.0	17.2 GB	view
16k	913.2	54.0	17.8 GB	view
32k	796.6	35.6	19.1 GB	current