← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M4 (10c) · 24 GB · 4bit · 2026-03-10

Performance

1k

tokens

122.2

PP tok/s

11.6

TG tok/s

8380

TTFT (ms)

8.4

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	122.2	11.6	8.4 GB	current
4k	117.2	10.7	9.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	11.6	1.00×
2×	18.9	1.63×
4×	27.6	2.38×