← Back to community benchmarks

Qwen3.5-4B

M2 Pro (16c) · 16 GB · 4bit · 2026-03-12

Performance

1k

tokens

316.9

PP tok/s

57.6

TG tok/s

3231

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 16 GB

GPU Cores 16

Software

oMLX v0.2.8

macOS macOS 15.7.5

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	316.9	57.6	4.0 GB	current
4k	316.1	53.1	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	57.6	1.00×
2×	69.2	1.20×
4×	63.0	1.09×