← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (40c) · 48 GB · 4bit · 2026-05-02

Performance

4k

tokens

1,426

PP tok/s

74.9

TG tok/s

2873

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 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	1,137	78.9	20.4 GB	view
4k	1,426	74.9	21.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	78.9	1.00×
2×	133.4	1.69×
4×	198.3	2.51×