← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 64 GB · 4bit · 2026-04-25

Performance

4k

tokens

1,673

PP tok/s

96.9

TG tok/s

2449

TTFT (ms)

21.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 15.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,128	98.6	20.4 GB	view
4k	1,673	96.9	21.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	98.6	1.00×
2×	113.2	1.15×
4×	211.8	2.15×