← Back to community benchmarks

Qwen3.6-35B-A3BoQ4

M2 Max (38c) · 64 GB · 4bit · 2026-04-17

Performance

4k

tokens

1,230

PP tok/s

76.7

TG tok/s

3330

TTFT (ms)

20.8

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 64 GB

GPU Cores 38

Software

oMLX v0.3.6

macOS macOS 15.7.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	882.0	80.3	20.0 GB	view
4k	1,230	76.7	20.8 GB	current
8k	1,241	70.8	21.1 GB	view
16k	1,185	64.6	21.8 GB	view