← Back to community benchmarks

Qwen3.5-4B

M2 Pro (16c) · 16 GB · 4bit · 2026-03-10

Performance

1k

tokens

315.6

PP tok/s

58.4

TG tok/s

3244

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 16 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	315.6	58.4	4.0 GB	current
4k	315.0	16.5	4.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.4	1.00×
2×	41.8	0.72×
4×	73.5	1.26×