click any column header to sort

TTS Bench — Speed — 2026-06-14_1328

Rig: windows-5090 — AMD Ryzen 9 9950X3D 16-Core Processor (16C) · NVIDIA GeForce RTX 5090 32GB · 126 GB RAM · Windows 11

Label: cloning · chris_hemsworth_15s · longcat_1b,longcat_3p5b — ref chris_hemsworth_15s.wav

TTFA = time to first audio (ms; lower is better). RTFx = realtime speed (× realtime; higher is better; e.g. 10× means 10 sec of audio generated per 1 sec of compute). Cold = first run after process start; warm = subsequent runs.

Speed winners

Fastest (this cloning run): LongCat-AudioDiT 1B (cuda) — 5.67× warm RTFx, 1.36s warm TTFA

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
LongCat-AudioDiT 1B	cuda	1.66s	1.36s	4.72×	5.67×	2.36 GB	5.78 GB	1.42B	Mar 2026
LongCat-AudioDiT 3.5B	cuda	2.59s	2.32s	3.13×	3.49×	2.26 GB	15.14 GB	3.83B	Mar 2026