← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Ultra (60c) · 256 GB · 4bit · 2026-04-27

Performance

4k

tokens

1,928

PP tok/s

84.9

TG tok/s

2125

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 256 GB

GPU Cores 60

Software

oMLX v0.3.6

macOS macOS 26.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,136	88.0	20.4 GB	view
4k	1,928	84.9	21.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	88.0	1.00×
2×	145.7	1.66×
4×	216.7	2.46×