← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

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

Performance

16k

tokens

1,496

PP tok/s

78.7

TG tok/s

10952

TTFT (ms)

21.7

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.7rc2

macOS macOS 26.4

Context 16,384

Performance by Context Length

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