← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-18

Performance

16k

tokens

1,721

PP tok/s

28.4

TG tok/s

9521

TTFT (ms)

23.5

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.6

macOS macOS 26.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	775.4	65.6	20.4 GB	view
4k	959.4	61.7	21.2 GB	view
8k	966.2	58.4	21.5 GB	view
16k	1,721	28.4	23.5 GB	current
32k	1,421	27.9	26.0 GB	view
64k	967.1	26.9	30.9 GB	view