← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M5 Pro (16c) · 24 GB · 4bit · 2026-04-15

Performance

1k

tokens

279.8

PP tok/s

15.6

TG tok/s

3660

TTFT (ms)

8.5

Peak mem (GB)

Hardware

Chip M5 Pro (16c)

Memory 24 GB

GPU Cores 16

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	279.8	15.6	8.5 GB	current
4k	301.7	12.9	9.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.6	1.00×
2×	20.6	1.32×
4×	26.1	1.67×