← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

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

Performance

4k

tokens

1,709

PP tok/s

107.7

TG tok/s

2397

TTFT (ms)

20.7

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 4,096

Performance by Context Length

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

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×