---
title: YuE2-Vae-fp32
canonical_url: "https://www.modelscope.cn/models/mlx-community/YuE2-Vae-fp32"
md_url: "https://www.modelscope.cn/models/mlx-community/YuE2-Vae-fp32.md"
repository: mlx-community/YuE2-Vae-fp32
last_updated: 2026-10-28
license: cc-by-nc-4.0
model_type:
  - yue2_vae
architectures:
  - YuE2VAE
base_model:
  - m-a-p/YuE2-Vae
base_model_relation: finetune
parameters: 66.4M
tensor_type:
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 37
stars: 0
tags:
  - mlx
  - swift
  - music-generation
  - yue2
  - vae
  - non-commercial
---

# YuE2-Vae-fp32

> YuE2-Vae-fp32 - mlx-community 在 ModelScope 开源的模型。Non-commercial weights (CC BY-NC 4.0). Songs made with YuE2 may not be sold, licensed or used in paid work, except under M-A-P's individual-creator permission (MODELLICENSE, 2026-09-16): personal users,…

mlx-community/YuE2-Vae-fp32 是 ModelScope 魔搭社区上的 66.4M 参数机器学习模型，采用 cc-by-nc-4.0 许可，基于 m-a-p/YuE2-Vae 构建。

- **Repository**: mlx-community/YuE2-Vae-fp32
- **License**: cc-by-nc-4.0
- **Parameters**: 66.4M
- **Base model**: m-a-p/YuE2-Vae
- **Tags**: mlx, swift, music-generation, yue2, vae, non-commercial
- **Downloads**: 37
- **Stars**: 0
- **Last updated**: 2026-10-28

Source: https://www.modelscope.cn/models/mlx-community/YuE2-Vae-fp32

---

# YuE2-Vae-fp32 (MLX)

> **Non-commercial weights (CC BY-NC 4.0).** Songs made with YuE2 may not be sold, licensed or used in paid work,
> **except** under M-A-P's *individual-creator permission* (MODEL_LICENSE, 2026-09-16): personal users, content
> creators and musicians acting in an individual capacity may publish, sell and license songs they make with it.
> Companies may not use the model commercially without a licence from M-A-P (ryuanab@connect.ust.hk), and a hosted
> service making songs for paying users is commercial use. Responsible use is a condition of the permission.

The listening VAE **decoder** of [m-a-p/YuE2-Vae](https://huggingface.co/m-a-p/YuE2-Vae) (M-A-P), converted for MLX.
It is used by [mlx-yue2-swift](https://github.com/xocialize/mlx-yue2-swift), the Swift-MLX port of YuE2-3B, together
with [mlx-community/YuE2-3B-bf16](https://huggingface.co/mlx-community/YuE2-3B-bf16) (usage on that card).
It is an Oobleck decoder: 64-dim latents at 25 Hz → 48 kHz stereo, fp32, decoded in exact tiles.

| file | size |
|---|---|
| `decoder.safetensors` (173 tensors, fp32; weight_norm folded, convs in MLX layout, encoder dropped) | 265 MB |
| `config.json` | 1.4 KB |
| `LICENSE` (HF, CC BY-NC 4.0), `MODEL_LICENSE` (GitHub, with the individual-creator permission), `NOTICE`, `THIRD_PARTY_NOTICES.md`, `licenses/` (Oobleck / SnakeBeta MIT) | — |

Parity: the folded tensors equal upstream's own `remove_weight_norm` output (max |Δ| 0). The Swift decode matches the
fp32 PyTorch oracle to relL2 ≤ 4.6e-6, and the tiled decode equals the full decode within 2.7e-6.

## Attribution

YuE2, YuE2-Vae, https://huggingface.co/m-a-p/YuE2-Vae, by M-A-P, under CC BY-NC 4.0. `NOTICE` lists exactly what changed
(the decoder only, weight_norm folded, layouts transposed). Not endorsed by M-A-P.