← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Pro (20c) · 48 GB · 4bit · 2026-05-20

Performance

4k

tokens

2,103

PP tok/s

94.9

TG tok/s

1948

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,139	97.7	19.3 GB	view
4k	2,103	94.9	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	97.7	1.00×
2×	149.2	1.53×
4×	197.5	2.02×