← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 6bit · 2026-05-19

Performance

64k

tokens

1,062

PP tok/s

64.4

TG tok/s

61700

TTFT (ms)

33.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,280	95.0	27.3 GB	view
4k	1,651	93.3	28.1 GB	view
64k	1,062	64.4	33.1 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	95.0	1.00×
2×	148.6	1.56×