Audio modelOpen weights

YuE2-3B

m-a-p

Released: -
Data date: October 3, 2026

Model class: Music generation
Access: Local weights

YuE2-3B generates complete songs from lyrics, style directions, and musical instructions. The open music checkpoint supports vocals and accompaniment, plus editable scores, melody and chord control, covers, and agentic editing.

Its documentation cites 24 GB of GPU memory for local execution. The weights use CC-BY-NC-4.0, so they are not unrestricted authorization for commercial music production.

Specifications and access

Specification	Value and source
Model class	Music generationSource
Access	Local weightsSource
Input	Lyrics, style, and musical directionSource
Output	Songs with vocals and accompanimentSource
Checkpoint	m-a-p/YuE2-3BSource
License	CC-BY-NC-4.0Source
Capabilities	Complete songs, editable score, melody and chord control, covers, and agentic editingSource
Hardware note	The documentation cites 24 GB of GPU memory for local executionSource
Repository	Official YuE repositorySource

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

PER (Show measurement, test conditions, and source)

Source value: 9.79
Score: 9.79
Metric: phoneme error rate
Unit: %
Benchmark version: best-of-8
Category: audio
Direction: Lower is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Same 192-prompt run
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

WildSongBench Musicality (Show measurement, test conditions, and source)

Source value: 6.2666
Score: 6.2666
Metric: score
Unit: No unit provided
Benchmark version: best-of-8
Category: audio
Direction: Higher is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. 192 prompts; candidates selected Musicality then Q3O then PER
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

WildSongBench SongBench average (Show measurement, test conditions, and source)

Source value: 6.9632
Score: 6.9632
Metric: score
Unit: No unit provided
Benchmark version: best-of-8
Category: audio
Direction: Higher is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. 192 prompts; candidates selected Musicality then Q3O then PER
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

WildSongBench MuLan (Show measurement, test conditions, and source)

Source value: 0.5051
Score: 0.5051
Metric: score
Unit: No unit provided
Benchmark version: best-of-8
Category: audio
Direction: Higher is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Same 192-prompt run
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

WildSongBench AllMusicCaps (Show measurement, test conditions, and source)

Source value: 0.398
Score: 0.398
Metric: score
Unit: No unit provided
Benchmark version: best-of-8
Category: audio
Direction: Higher is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Same 192-prompt run
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

WildSongBench Q3O (Show measurement, test conditions, and source)

Source value: 4.7009
Score: 4.7009
Metric: score
Unit: No unit provided
Benchmark version: best-of-8
Category: audio
Direction: Higher is better
Source type: vendor-reported
Evaluator: YuE2 model card
Status: active
Retrieved at: 2026-10-04
Methodology: Vendor-reported result. Same 192-prompt run
Context: Source-specific observation; it does not establish a compatible cross-model cohort.

Source YuE2 model card

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Type	Evidence and data date
Research status	Research date October 4, 2026. 1 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Additional source	YuE2-3B model card (retrieved October 3, 2026; October 4, 2026) · YuE2-3B model card · Editorial description reviewed October 3, 2026
Additional source	YuE repository (retrieved October 3, 2026) · YuE repository · Editorial description reviewed October 3, 2026