← Back to community benchmarks

Phi-4-reasoning-plus

M4 Pro (16c) · 24 GB · 4bit · 2026-03-16

Performance

4k

tokens

177.2

PP tok/s

24.8

TG tok/s

23111

TTFT (ms)

10.0

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.2.12

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	183.8	28.2	8.6 GB	view
4k	177.2	24.8	10.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.2	1.00×
2×	43.9	1.56×
4×	46.4	1.65×