← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Ultra (80c) · 512 GB · 4bit · 2026-05-10

Performance

1k

tokens

1,675

PP tok/s

91.6

TG tok/s

612

TTFT (ms)

19.2

Peak mem (GB)

Hardware

Chip M3 Ultra (80c)

Memory 512 GB

GPU Cores 80

Software

oMLX v0.3.9.dev1

macOS macOS 15.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,675	91.6	19.2 GB	current
4k	2,482	88.3	20.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	91.6	1.00×
2×	158.1	1.73×
4×	261.8	2.86×