← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (80c) · 96 GB · 4bit · 2026-04-24

Performance

16k

tokens

2,553

PP tok/s

80.1

TG tok/s

6418

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 96 GB

GPU Cores 80

Software

oMLX v0.3.7

macOS macOS 26.3.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,531	96.5	19.2 GB	view
4k	2,550	94.0	20.0 GB	view
8k	2,684	88.5	20.4 GB	view
16k	2,553	80.1	21.0 GB	current
32k	2,207	63.3	22.4 GB	view