← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

M1 Max (32c) · 64 GB · 4bit · 2026-04-29

Performance

16k

tokens

726.4

PP tok/s

49.7

TG tok/s

22554

TTFT (ms)

21.8

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.3.8rc1

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	612.9	190.8	21.4 GB	view
4k	513.4	62.1	20.9 GB	view
8k	783.2	58.3	21.2 GB	view
16k	726.4	49.7	21.8 GB	current
32k	624.0	38.9	23.2 GB	view
64k	437.4	25.1	25.9 GB	view