← Back to community benchmarks

orpheus-3b-0.1-ft

M5 Pro (20c) · 64 GB · 8bit · 2026-03-17

Performance

4k

tokens

987.1

PP tok/s

50.5

TG tok/s

4150

TTFT (ms)

4.4

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.14

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	965.6	46.1	3.9 GB	view
4k	987.1	50.5	4.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	46.1	1.00×
2×	55.6	1.21×
4×	100.0	2.17×