YU

quantized-yue2-3b

YueGGUF by ngquocvinhUpdated 2026-09-13
Download on Hugging Face
Parameters3.63B
Context—
Layers—
Architectureaudiocpp
Smallest quant0.3 GB
Quick answer

quantized-yue2-3b needs about 3.7 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 21 quants, from 0.3 GB (F16) to 7.3 GB (BF16).

Quantized YuE2-3B music generation model

YuE2-3B is a 3.63 billion‑parameter music generation model that turns lyrics and style prompts into 48 kHz stereo songs. The GGUF quantizations enable local inference with a variety of precision levels.

Good at

  • Text‑to‑music generation
  • Editable score editing
  • High‑quality stereo output

Limits

  • Requires separate VAE GGUF file
  • No vision support
  • CC‑BY‑NC‑4.0 license

Best for

  • Creating original songs from lyrics
  • Editing melodies and chords
  • Running locally on GPUs with 24 GB VRAM

Who it’s for. Users who need a local, open‑source music generation model for creative projects. The model is suitable for musicians, producers, and developers building music tools.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.3 GB 0.8 GB
Fits Get file →
F320.5 GB 1.1 GB
Fits Get file →
Q2_K1.9 GB 2.6 GB
Fits Get file →
Q2_K_S2.1 GB 2.9 GB
Fits Get file →
Q3_K2.2 GB 3.0 GB
Fits Get file →
Q3_K_S2.4 GB 3.1 GB
Fits Get file →
Q3_K_M2.5 GB 3.2 GB
Fits Get file →
Q3_K_L2.6 GB 3.4 GB
Fits Get file →
Q4_02.7 GB 3.5 GB
Fits Get file →
Q4_K2.7 GB 3.5 GB
Fits Get file →
Q4_12.9 GB 3.7 GB
Fits Get file →
Q4_K_M2.9 GB 3.7 GB
Fits Get file →
Q5_03.1 GB 3.9 GB
Fits Get file →
Q5_K3.1 GB 3.9 GB
Fits Get file →
Q5_K_M3.2 GB 4.1 GB
Fits Get file →
Q5_13.3 GB 4.2 GB
Fits Get file →
Q6_K3.5 GB 4.4 GB
Fits Get file →
Q6_K_M3.7 GB 4.6 GB
Fits Get file →
Q8_04.3 GB 5.3 GB
Fits Get file →
Q8_05.0 GB 6.1 GB
Fits Get file →
BF167.3 GB 8.6 GB
Too big Get file →

For 8 GB VRAM, use Q4_K (file size 2.67 GB, memory 3.5 GB). For 12 GB VRAM, Q5_K_M (3.17 GB, 4.1 GB). For 24 GB VRAM, the unquantized F32 (0.53 GB, 1.1 GB) or Q8_0 (4.26 GB, 5.3 GB) provide the best quality.

What GPU do you need for quantized-yue2-3b?

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 Q5_K (3.1 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (4.3 GB file, about 5.3 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (5.0 GB file, about 6.1 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 8.6 GB in use).

Which quantized-yue2-3b quant should you choose?

Q4_K_M is the usual starting point for quantized-yue2-3b: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 4.3 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is F16 at 0.3 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureaudiocpp
Parameters3.63B

Source

Quantized byngquocvinh
FamilyYue
Base modelm-a-p/YuE2-3B
Downloads (HF)7,013
Last updated2026-09-13

Frequently asked questions about quantized-yue2-3b

How much VRAM does quantized-yue2-3b need?

About 3.7 GB at Q4_K_M with an 8K context window. That is the 2.9 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 quantized-yue2-3b on an 8 GB GPU?

Yes, with Q8_0: the 5.0 GB file needs about 6.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of quantized-yue2-3b GGUF?

It depends on the quant: F16 is 0.3 GB, F32 is 0.5 GB, Q2_K is 1.9 GB, Q2_K_S is 2.1 GB, Q3_K is 2.2 GB, Q3_K_S is 2.4 GB and 15 more.

Where can I download quantized-yue2-3b GGUF?

The files are on Hugging Face in the ngquocvinh/YuE2-3B-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 quantized-yue2-3b 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 YuE2-3B on 8 GB VRAM?

Yes, using the Q4_K quantization which requires about 3.5 GB of VRAM at 8k context.

Do I need a separate VAE file?

Yes, the main model and VAE are separate GGUF components and must be kept together.

Is the model open source?

The model is released under CC‑BY‑NC‑4.0 and can be used for non‑commercial purposes.

Other GGUFs of YuE2-3B

Similar models

Browse all →

More from ngquocvinh

All by ngquocvinh →

More Yue models

All Yue →

Other small models

All small models →