← Back to community benchmarks

Qwen3.6-35B-A3B-TurboQuant

M3 Max (40c) · 64 GB · 4bit · 2026-05-20

Performance

4k

tokens

1,434

PP tok/s

89.1

TG tok/s

2857

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,068	87.5	19.2 GB	view
4k	1,434	89.1	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.5	1.00×
2×	151.3	1.73×
4×	222.6	2.54×