← Back to community benchmarks

Qwen3.5-2B

M3 Pro (14c) · 18 GB · 6bit · 2026-03-10

Performance

4k

tokens

1,231

PP tok/s

67.2

TG tok/s

3329

TTFT (ms)

3.2

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.2.6

macOS macOS 15.3.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,187	72.0	3.1 GB	view
4k	1,231	67.2	3.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	72.0	1.00×
2×	132.6	1.84×
4×	142.0	1.97×