HKUSTAudio/Llasa-1B download history

HKUSTAudio/Llasa-1B is a 1.4B-parameter text to speech model by HKUSTAudio. In the last 30 days it was downloaded 1,243 times (338 in the last 7 days), and 157,056 times in total.

It ranks #30,364 on the Hub by monthly downloads and #511 among text to speech models.

It has 103 likes.

It is a fine-tune of meta-llama/Llama-3.2-1B-Instruct.

14 models build on Llasa-1B: 6 quantized, 4 fine-tuned, 4 adapters and 0 merges. Together with the original they were downloaded 2,255 times in the last 30 days. See the Llasa-1B galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-181,243+25%
October 2026995-6%
September 20261,061+176%
August 2026384-81%
July 20262,059+22%
June 20261,694+51%
May 20261,120-87%
April 20268,503-24%
March 202611,202-15%
February 202613,143-14%
January 202615,265-26%
December 202520,520+248%

Its busiest 30 days so far ended on 2025-12-30, with 20,753 downloads.

Open HKUSTAudio/Llasa-1B on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.