← Back to community benchmarks

Qwen3.6-35B-A3B-4bit-DWQ

M5 Pro (20c) · 48 GB · 8bit · 2026-04-26

Performance

1k

tokens

1,438

PP tok/s

74.9

TG tok/s

712

TTFT (ms)

20.3

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,438	74.9	20.3 GB	current
4k	2,128	72.2	21.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	74.9	1.00×
2×	119.5	1.60×
4×	168.6	2.25×