← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-04-28

Performance

1k

tokens

1,558

PP tok/s

309.9

TG tok/s

657

TTFT (ms)

29.4

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,558	309.9	29.4 GB	current
4k	1,268	98.1	28.9 GB	view
8k	3,891	95.4	29.2 GB	view
16k	3,760	88.8	29.9 GB	view
32k	3,225	75.5	31.2 GB	view