Models/YuE2 · 3B

Audio / Multimodal Art Projection

YuE2 · 3B

Create a full song from style and lyrics with a publisher Python package on a Linux NVIDIA GPU; outputs include a playable FLAC.

Verified sourceReleased Sep 9, 2026Source checked 10/14/2026

LOCALRENTED GPUOPEN WEIGHTS

Freshness 87 out of 100. Release age: 36 days old, Sep 9, 2026. Measures age, not quality.

Popularity 64 out of 100. 33,535 downloads in 30 days; 1,152 lifetime likes. Checked Oct 15, 2026. Measures adoption, not quality.

What do these scores mean?

Two ways to compare models. Neither score measures answer quality, benchmark performance, or whether a model fits your machine.

Freshness · release age

A new release starts at 100. The score halves every 180 days: 100 × 2^(−age in days / 180). When the release date is unavailable, a repository date is a fallback—not proof of when the model was released. Missing dates stay unscored.

Check the date source

Popularity · adoption

Downloads over the past 30 days carry 80% of the score; lifetime likes carry 20%. Both use a logarithmic scale, capped at 10 million downloads and 100,000 likes. If likes are unavailable, downloads carry all the weight. Missing download statistics stay unscored.

round(80 × min(1, log10(1 + downloads) / 7) + 20 × min(1, log10(1 + likes) / 5))

Check the statistics source

Scores as of Oct 15, 2026. Statistics checked Oct 15, 2026. Statistics are marked for refresh after 72 hours.Full scoring method

WORKFLOWS FOR THIS MODEL 1

What do you want to do?

Choose a task. Get the software, files, settings, and steps to run it.

MAKE IT PERSONALChoose your hardware

Audio

Create a song locally with YuE2 3B

Create a local song visually with the official ComfyUI YuE2 template and exact 3B int8 checkpoint; publisher Linux wheel and community audio.cpp are available as alternate routes.

Freshness 87 out of 100. Release age: 36 days old, Sep 9, 2026. Measures age, not quality.

ComfyUIYuE2 inference wheel

3 packagesmacOS / Windows / Linux

Open setup guide

Open a guide for its software, hardware requirements, and setup steps.

At a glance

Parameters: 3B
License: CC BY-NC 4.0 · noncommercial
Software: YuE2 inference wheel, Python

MY HARDWARE

Will it run on your machine?

Save your machine to see a personalized rating and its reasoning.

Add my hardware

Best for

Private song generation from lyrics and style prompts.

Tradeoffs

Noncommercial license; review it before business use.
Publisher has not documented a native Mac or Windows inference path.

Ways to run it

Publisher YuE2 Python package · Linux · NVIDIA BF16 GPU

Publisher quick start calls for Python 3.10+, 24 GB GPU and 24 GB available host RAM; a Mac/Windows user can rent a Linux GPU.

hf download m-a-p/YuE2-3B yue2_infer-0.1.5-py3-none-any.whl --local-dir .

Official instructions

Explore its uses

MUSIC GENERATIONVOCALSLYRICSLOCAL AUDIO

REFERENCE LIBRARY

Sources and files

Primary sources and files behind this model page.

1 SOURCE

01YuE2 quick start, resources and licensehuggingface.co

Keep exploring

Audio

Mistral AI

Voxtral Mini · 4B Realtime

Voxtral Mini 4B Realtime 2602 is a multilingual, realtime automatic speech recognition model from Mistral AI, released under the Apache-2.0 license. It features a natively streaming architecture with a causal audio encoder and sliding window attention, enabling configurable transcription delays from 240ms to 2.4s (and reportedly 80ms to 2.4s). The model has approximately 4B parameters (≈3.4B language model and ≈970M audio encoder) and is described as optimized for on-device deployment. It supports 13 languages and is presented as achieving accuracy comparable to offline systems with less than 500ms delay, specifically matching leading offline open-source models and realtime APIs at a 480ms delay. The model card recommends a temperature of 0.0, using websockets for audio streaming, and a delay of 480ms as a balance between performance and latency.

Freshness 36 out of 100. Repository age: 267 days old, Jan 21, 2026. Measures age, not quality.

MODEL SIZE4B

LOCALRENTED GPU

Repository opened Jan 21, 2026

Audio

ibm-granite

granite speech 5.0 470m turboctc

Granite Speech 5.0 470M TurboCTC is a compact 470 million parameter English automatic speech recognition model released by IBM under the Apache 2.0 license. It uses a conformer acoustic encoder with block self-attention, self-conditioning, and temporal downsampling, with an output layer of 16,384 BPE units. The model was trained on approximately 60,000 hours of English audio from public corpora using Connectionist Temporal Classification (CTC), and inference is non-autoregressive with greedy decoding. It is designed for low-latency and high-throughput English speech-to-text transcription, and is described as suitable for deployment on laptops, smartphones, and other edge devices. Native support is available in transformers>=5.16.0, with additional usage options for Apple Silicon via mlx-audio and local GGUF inference via transcribe.cpp.

Freshness 76 out of 100. Repository age: 72 days old, Aug 4, 2026. Measures age, not quality.

MODEL SIZE0.47B

LOCALRENTED GPU

Repository opened Aug 4, 2026

Audio

openai

Whisper

Explore 6 versions of Whisper. Compare model sizes, packages, hardware requirements, and available setups.

6 versionsCompare sizes & formats

LOCALRENTED GPU

Compare versions →