← Back to community benchmarks

Qwen2.5-0.5B-Instruct

M1 Pro (16c) · 32 GB · unknown · 2026-03-11

Performance

1k

tokens

1,900

PP tok/s

125.6

TG tok/s

539

TTFT (ms)

1.5

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.2.7

macOS macOS 15.7.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,900	125.6	1.5 GB	current
4k	2,767	107.5	1.7 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	125.6	1.00×
2×	101.1	0.80×
4×	186.0	1.48×