← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (30c) · 96 GB · 4bit · 2026-04-19

Performance

16k

tokens

1,012

PP tok/s

64.6

TG tok/s

16196

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 96 GB

GPU Cores 30

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	938.9	87.3	19.3 GB	view
4k	1,141	82.2	20.0 GB	view
8k	1,127	76.7	20.4 GB	view
16k	1,012	64.6	21.0 GB	current