← Back to community benchmarks

Qwen3.5-2B

M4 Pro (20c) · 64 GB · 8bit · 2026-03-10

Performance

1k

tokens

1,869

PP tok/s

105.2

TG tok/s

548

TTFT (ms)

3.4

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,869	105.2	3.4 GB	current
4k	1,973	96.6	3.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	105.2	1.00×
2×	195.7	1.86×
4×	274.8	2.61×