← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 48 GB · 4bit · 2026-04-30

Performance

4k

tokens

2,247

PP tok/s

96.4

TG tok/s

1823

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,515	100.0	19.3 GB	view
4k	2,247	96.4	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	100.0	1.00×
2×	153.0	1.53×
4×	201.2	2.01×