← Back to community benchmarks

community--Qwen3.6-35B-A3B

M1 Pro (14c) · 32 GB · 4bit · 2026-06-07

Performance

1k

tokens

233.1

PP tok/s

43.6

TG tok/s

4392

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 32 GB

GPU Cores 14

Software

oMLX v0.4.1

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	233.1	43.6	19.2 GB	current
4k	259.0	42.1	19.4 GB	view
8k	269.6	38.2	20.4 GB	view
16k	257.6	33.5	21.0 GB	view
32k	232.9	26.2	22.4 GB	view
64k	175.0	17.0	22.4 GB	view