← Back to community benchmarks

Qwen3.6-35B-A3BoQ6

M4 Max (40c) · 64 GB · 6bit · 2026-05-15

Performance

8k

tokens

818.1

PP tok/s

47.4

TG tok/s

10014

TTFT (ms)

28.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	725.2	141.9	28.9 GB	view
4k	440.2	49.4	28.4 GB	view
8k	818.1	47.4	28.9 GB	current