← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M4 Max (40c) · 64 GB · 6bit · 2026-04-19

Performance

1k

tokens

1,372

PP tok/s

285.5

TG tok/s

746

TTFT (ms)

29.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,372	285.5	29.1 GB	current
4k	549.9	88.3	28.5 GB	view
8k	1,663	84.2	28.9 GB	view
16k	1,523	76.8	29.5 GB	view
32k	1,200	51.7	30.8 GB	view
64k	983.1	33.4	33.5 GB	view
128k	542.0	19.2	38.9 GB	view