← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M4 Pro (16c) · 64 GB · 4bit · 2026-03-12

Performance

1k

tokens

189.3

PP tok/s

25.1

TG tok/s

5410

TTFT (ms)

8.5

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 64 GB

GPU Cores 16

Software

oMLX v0.2.9

macOS macOS 26.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	189.3	25.1	8.5 GB	current
4k	180.5	22.6	9.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	25.1	1.00×
2×	41.8	1.67×
4×	43.8	1.75×