← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M1 Ultra (48c) · 128 GB · 4bit · 2026-04-17

Performance

16k

tokens

2,318

PP tok/s

37.6

TG tok/s

7067

TTFT (ms)

22.7

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 128 GB

GPU Cores 48

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	992.7	70.2	20.4 GB	view
4k	1,351	59.6	21.2 GB	view
8k	1,381	61.9	21.5 GB	view
16k	2,318	37.6	22.7 GB	current