← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (80c) · 512 GB · 8bit · 2026-04-28

Performance

1k

tokens

2,240

PP tok/s

324.3

TG tok/s

457

TTFT (ms)

36.1

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.8rc1

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,240	324.3	36.1 GB	current
4k	1,982	295.3	37.2 GB	view
8k	1,586	308.6	37.4 GB	view
16k	1,234	270.0	38.0 GB	view
32k	927.6	192.1	39.2 GB	view