← Back to community benchmarks

Qwen2.5-Coder-7B-Instruct

M2 Pro (16c) · 32 GB · 4bit · 2026-05-18

Performance

4k

tokens

309.8

PP tok/s

36.4

TG tok/s

13223

TTFT (ms)

4.9

Peak mem (GB)

Hardware

Chip M2 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.3.8

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	307.2	39.4	4.8 GB	view
4k	309.8	36.4	4.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	39.4	1.00×
2×	56.0	1.42×
4×	57.8	1.47×