← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmixed-6.4bit

M4 Pro (16c) · 48 GB · 6bit · 2026-04-20

Performance

64k

tokens

443.9

PP tok/s

27.3

TG tok/s

147630

TTFT (ms)

32.4

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	634.8	60.0	26.6 GB	view
4k	727.3	57.3	27.4 GB	view
8k	714.9	54.1	27.7 GB	view
16k	664.2	47.4	28.3 GB	view
32k	572.2	37.0	29.7 GB	view
64k	443.9	27.3	32.4 GB	current