← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Pro (20c) · 48 GB · 4bit · 2026-04-29

Performance

195k

tokens

69.1

PP tok/s

12.4

TG tok/s

2894227

TTFT (ms)

34.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.7rc2

macOS macOS 15.7.5

Context 200,000

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	695.8	200.1	21.3 GB	view
4k	622.3	195.6	22.3 GB	view
8k	595.5	158.1	22.5 GB	view
16k	442.3	125.9	23.1 GB	view
32k	288.5	72.2	24.3 GB	view
64k	180.3	55.6	26.7 GB	view
128k	79.9	18.9	30.8 GB	view
195k	69.1	12.4	34.8 GB	current