← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Pro (14c) · 36 GB · 4bit · 2026-04-17

Performance

32k

tokens

263.4

PP tok/s

30.6

TG tok/s

124411

TTFT (ms)

20.6

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 36 GB

GPU Cores 14

Software

oMLX v0.3.5

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	462.0	50.7	19.2 GB	view
4k	549.2	49.9	20.0 GB	view
8k	438.7	46.6	20.1 GB	view
16k	362.3	42.9	20.3 GB	view
32k	263.4	30.6	20.6 GB	current
64k	168.8	14.4	21.2 GB	view
128k	95.8	5.3	22.4 GB	view