← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M4 Pro (16c) · 24 GB · 4bit · 2026-03-10

Performance

4k

tokens

188.6

PP tok/s

23.6

TG tok/s

21715

TTFT (ms)

9.2

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	199.0	27.1	8.5 GB	view
4k	188.6	23.6	9.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.1	1.00×
2×	43.5	1.61×
4×	46.2	1.70×