← Back to community benchmarks

Qwen3.6-35B-A3B-q4

M4 Max (40c) · 64 GB · 4bit · 2026-04-16

Performance

16k

tokens

3,244

PP tok/s

46.0

TG tok/s

5050

TTFT (ms)

22.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,441	213.9	20.6 GB	view
4k	691.7	99.5	20.8 GB	view
8k	1,600	94.1	21.1 GB	view
16k	3,244	46.0	22.3 GB	current
32k	3,186	44.8	22.9 GB	view
64k	2,432	43.9	24.8 GB	view
128k	1,764	39.3	27.4 GB	view