← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Max (40c) · 64 GB · 4bit · 2026-04-23

Performance

8k

tokens

1,633

PP tok/s

88.9

TG tok/s

5017

TTFT (ms)

21.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7rc2

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,633	88.9	21.1 GB	current
16k	1,496	78.7	21.7 GB	view
32k	1,207	64.9	23.0 GB	view