← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M4 Max (40c) · 48 GB · 4bit · 2026-05-18

Performance

1k

tokens

1,204

PP tok/s

111.7

TG tok/s

850

TTFT (ms)

19.9

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,204	111.7	19.9 GB	current
4k	1,709	107.7	20.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	111.7	1.00×
2×	177.1	1.59×
4×	239.4	2.14×
8×	300.2	2.69×