← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Pro (16c) · 64 GB · 4bit · 2026-04-29

Performance

64k

tokens

1,115

PP tok/s

22.3

TG tok/s

58786

TTFT (ms)

44.3

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.3.8rc1

macOS macOS 26.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	579.4	155.4	39.8 GB	view
4k	125.5	68.1	40.3 GB	view
8k	654.6	61.9	40.7 GB	view
16k	1,523	24.2	41.8 GB	view
32k	1,350	23.2	42.4 GB	view
64k	1,115	22.3	44.3 GB	current