YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong needs about 1.5 GB of memory at Q8_0 (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.0 GB (Q8_0) to 7.2 GB (BF16).
YuE2 audio tokenizer – 0.632B parameter semantic‑token encoder
YuE2 audio tokenizer converts recordings into semantic tokens for YuE2‑3B. It is part of the Mothersuperior family and uses a 8‑layer encoder. The model is licensed cc‑by‑nc‑4.0 and is available as GGUF files.
Good at
- Tokenizes audio for YuE2 generation
- Supports LoRA‑tuned decoding
- Compatible with yue2.cpp
Limits
- No vision support
- Requires 8‑k context for estimates
- License restricts commercial use
Best for
- Audio preprocessing for song generation
- Preparing data for LoRA fine‑tuning
- Transcribing recordings to semantic codes
Who it’s for. Developers building YuE2‑based music generation pipelines. Users who need a lightweight tokenizer to feed audio into the YuE2 architecture. Those who want to experiment with LoRA tuning of the decoder.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.0 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F32 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| F32 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| F32 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| F32 | 2.5 GB | 3.3 GB | Fits | Get file → | |
| Q5_K_M | 2.6 GB | 3.4 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q8_0 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → |
For 8‑GB VRAM use Q8_0 (0.05 GB) or Q5_K_M (2.62 GB) depending on memory budget. Q8_0 gives near‑lossless performance. Q5_K_M reduces size while keeping acceptable quality. Larger models like BF16 (7.17 GB) require more VRAM.
What GPU do you need for YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (2.9 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (3.8 GB file, about 4.8 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.2 GB file, about 8.5 GB in use).
Which YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong quant should you choose?
Q8_0 (0.9 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q8_0 at 0.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong
How much VRAM does YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong need?
About 1.5 GB at Q8_0 with an 8K context window. That is the 0.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong on an 8 GB GPU?
Yes, with Q8_0: the 3.8 GB file needs about 4.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong GGUF?
It depends on the quant: Q8_0 is 0.0 GB, Q8_0 is 0.1 GB, F32 is 0.2 GB, F32 is 0.2 GB, F32 is 0.5 GB, Q8_0 is 0.9 GB and 5 more.
Where can I download YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong GGUF?
The files are on Hugging Face in the Serveurperso/YuE2-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does YuE2 audio tokenizer, the v9 head of Mothersuperior, on MERT-v2-FullSong use?
Hugging Face lists the license as cc-by-nc-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run the tokenizer on 8 GB VRAM?
Yes, the Q8_0 quantization file is 0.05 GB and requires about 0.6 GB memory at 8k context, well within 8 GB.
Does the tokenizer support multi‑channel audio?
It outputs stereo 48 kHz audio tokens; input is mono or stereo, but the model is designed for 48 kHz.
Is the model free to use commercially?
No, the cc‑by‑nc‑4.0 license prohibits commercial use without permission.