← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M5 Max (40c) · 64 GB · 4bit · 2026-04-24

Performance

32k

tokens

3,314

PP tok/s

87.0

TG tok/s

9888

TTFT (ms)

23.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8.dev1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,618	125.9	19.9 GB	view
16k	3,893	102.9	21.7 GB	view
32k	3,314	87.0	23.0 GB	current