← Back to community benchmarks

Qwen3.5-4B

M3 Pro (14c) · 18 GB · 4bit · 2026-03-13

Performance

4k

tokens

494.7

PP tok/s

46.6

TG tok/s

8279

TTFT (ms)

4.2

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	492.3	49.2	4.0 GB	view
4k	494.7	46.6	4.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	49.2	1.00×
2×	94.0	1.91×
4×	113.8	2.31×