Skip to content

Trending AI Today

fishaudio/drama-3

Model · Text to speech · edition of October 24, 2026

fishaudio/drama-3 is a text to speech model published by fishaudio on Hugging Face. At the collection of October 24, 2026 it was No. 7 on the trending list, with 17,017 downloads in 30 days and 955 likes.

Collected · snapshot shipped with the site build, not a live feed

Why it is on the list

  • No. 7 by Hugging Face trending score (364)
  • +2 likes since 2026-10-23
  • 17,017 downloads in the last 30 days

17Kdownloads in 30 days

955likes

Since October 23, 2026: +0 downloads (30-day figure), +2 likes

Positions and counts are Hugging Face’s; we report them and add no score of our own.

Open on Hugging Face (opens in a new tab)

Source: Hugging Face public API · updated

Fact sheet

Licence
Other (custom terms) · Read the termsCustom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use.
Size
35,899,643,008 parametersAbout 71.8 GB of weights at 16 bits; about 20.2 GB at a typical 4-bit quantisation.
Formats and library
safetensors
Access
Open download
Created · last changed
·
Downloads, all time
17,017

Most downloaded quantisations

Repositories that declare this model as base

Questions about drama-3

Why is fishaudio/drama-3 trending?

No. 7 by Hugging Face trending score (364); +2 likes since 2026-10-23; 17,017 downloads in the last 30 days. Hugging Face does not publish the formula of its trending score; these are the public figures behind the position.

Can drama-3 be used commercially?

The repository is tagged with the licence "Other (custom terms)". Custom or use-restricted terms (for example OpenRAIL, Llama, Gemma or a vendor licence). Read the licence text before commercial use. The tag is set by the uploader, so confirm it against the licence file in the repository.

How large is drama-3?

35.9B parameters according to the safetensors metadata. Weights alone take about 72 GB at 16 bits per parameter and about 20 GB in a typical 4-bit quantisation, before the memory needed for the context.

Are there quantised versions of drama-3?

Yes. The most downloaded repositories that declare fishaudio/drama-3 as their base are Jmica/Drama-3-GGUF (27K downloads in 30 days), sakasegawa/drama-3-GGUF (23.8K downloads in 30 days), Eng-Ahmd/Drama-3-Windows-GGUF (16.5K downloads in 30 days).