← Back to community benchmarks

Qwen3.5-2B

M4 Pro (20c) · 48 GB · 8bit · 2026-05-04

Performance

1k

tokens

1,417

PP tok/s

105.4

TG tok/s

723

TTFT (ms)

2.8

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 48 GB

GPU Cores 20

Software

oMLX v0.3.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,417	105.4	2.8 GB	current
4k	1,900	101.5	3.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	105.4	1.00×
2×	197.5	1.87×
4×	276.7	2.63×