← Back to community benchmarks

Qwen3.6-35B-A3B-UD-Q5_K_XL

M5 Pro (16c) · 48 GB · 5bit · 2026-04-18

Performance

4k

tokens

1,651

PP tok/s

61.2

TG tok/s

2480

TTFT (ms)

26.4

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,022	64.6	25.6 GB	view
4k	1,651	61.2	26.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.6	1.00×
2×	89.5	1.39×