click any column header to sort

TTS Bench — Speed — 2026-06-22_2116

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

Label: default voice · lfm2_audio

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 predefined-voice: LFM2.5-Audio 1.5B (cpu) — 1.26× warm RTFx, 84ms warm TTFA

Fastest cloning-capable: no data

Model	Device	TTFA cold	TTFA warm	RTFx cold	RTFx warm	Peak RAM	Peak VRAM	Size	Released
LFM2.5-Audio 1.5B	cpu	391ms	84ms	1.02×	1.26×	2.25 GB	—	1.5B	Dec 2025
LFM2.5-Audio 1.5B	cuda	410ms	91ms	0.99×	1.18×	2.25 GB	3.18 GB	1.5B	Dec 2025