HKUSTAudio/Llasa-3B download history

HKUSTAudio/Llasa-3B is a 4.0B-parameter text to speech model by HKUSTAudio. In the last 30 days it was downloaded 180 times (61 in the last 7 days), and 37,156 times in total.

It ranks #130,176 on the Hub by monthly downloads and #1,362 among text to speech models.

It has 531 likes.

It is a fine-tune of meta-llama/Llama-3.2-3B-Instruct.

22 models build on Llasa-3B: 16 quantized, 6 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 3,162 times in the last 30 days. See the Llasa-3B 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 2026-11-18180-6%
October 2026191-45%
September 2026347-66%
August 20261,034-11%
July 20261,166+291%
June 2026298+83%
May 2026163+25%
April 2026130-68%
March 2026403-64%
February 20261,130+60%
January 2026707-51%
December 20251,435+102%

Its busiest 30 days so far ended on 2025-02-21, with 8,847 downloads.

Open HKUSTAudio/Llasa-3B on Hugging Face

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