← Back to community benchmarks

Qwen2.5-1.5B-Instruct

M2 Pro (19c) · 32 GB · unknown · 2026-03-12

Performance

1k

tokens

1,113

PP tok/s

49.9

TG tok/s

920

TTFT (ms)

3.4

Peak mem (GB)

Hardware

Chip M2 Pro (19c)

Memory 32 GB

GPU Cores 19

Software

oMLX v0.2.6

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,113	49.9	3.4 GB	current
4k	1,326	48.1	3.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	49.9	1.00×
2×	48.9	0.98×
4×	92.9	1.86×