← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-05-18

Performance

4k

tokens

1,656

PP tok/s

81.9

TG tok/s

2474

TTFT (ms)

36.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9.dev2

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,145	84.2	35.4 GB	view
4k	1,656	81.9	36.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	84.2	1.00×
2×	134.9	1.60×
4×	203.9	2.42×