← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (40c) · 64 GB · 4bit · 2026-05-14

Performance

4k

tokens

1,438

PP tok/s

78.6

TG tok/s

2849

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	958.3	80.4	20.4 GB	view
4k	1,438	78.6	21.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.4	1.00×
2×	132.4	1.65×
4×	197.5	2.46×