← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-28

Performance

4k

tokens

2,315

PP tok/s

71.0

TG tok/s

1770

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.24

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,991	76.0	20.1 GB	view
4k	2,315	71.0	21.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	76.0	1.00×
2×	122.8	1.62×
4×	175.7	2.31×