← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M4 Max (40c) · 128 GB · 8bit · 2026-04-28

Performance

32k

tokens

499.5

PP tok/s

132.0

TG tok/s

65599

TTFT (ms)

85.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,207	210.1	36.1 GB	view
4k	960.4	267.7	39.7 GB	view
8k	970.6	244.9	43.6 GB	view
16k	835.6	191.9	52.4 GB	view
32k	499.5	132.0	85.9 GB	current