← Back to community benchmarks

Qwen3.6-35B-A3B-UD-Q6_K_XL

M5 Pro (16c) · 48 GB · 6bit · 2026-04-23

Performance

1k

tokens

1,582

PP tok/s

62.6

TG tok/s

647

TTFT (ms)

31.4

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.13

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,582	62.6	31.4 GB	current
4k	1,737	61.6	31.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	62.6	1.00×
2×	93.6	1.50×
4×	128.7	2.06×