HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

tada-3b-ml

HumeAI/tada-3b-ml

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-to-speech
root model
meta-llama/Llama-3.2-3B
provider
HumeAI
license
llama3.2
language
en, ja, de, fr, es, ch, ar, it, pl, pt
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
7,992
likes
159
created
—
last modified
2026-03-17T18:09:08+00:00 (2026)
huggingface
https://huggingface.co/HumeAI/tada-3b-ml
tags
safetensorsllamattstext-to-speechspeech-language-modelenjadefrescharitplptarxiv:2602.23068base_model:meta-llama/Llama-3.2-3Bbase_model:finetune:meta-llama/Llama-3.2-3Blicense:llama3.2region:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.