← Back to community benchmarks

Qwen2.5-Coder-7B-Instruct

M1 Pro (14c) · 32 GB · 4bit · 2026-04-20

Performance

4k

tokens

243.6

PP tok/s

33.4

TG tok/s

16817

TTFT (ms)

4.9

Peak mem (GB)

Hardware

Chip M1 Pro (14c)

Memory 32 GB

GPU Cores 14

Software

oMLX v0.3.6

macOS macOS 15.6.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	235.2	36.4	4.8 GB	view
4k	243.6	33.4	4.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	36.4	1.00×
2×	47.2	1.30×
4×	49.8	1.37×