← Back to community benchmarks

Qwen2.5-Coder-14B-Instruct

M1 Pro (16c) · 32 GB · 8bit · 2026-04-15

Performance

1k

tokens

134.7

PP tok/s

10.8

TG tok/s

7604

TTFT (ms)

15.3

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 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	134.7	10.8	15.3 GB	current
4k	134.4	9.5	16.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.8	1.00×
2×	17.7	1.64×
4×	19.1	1.77×