YU

YuE2 LM

YueGGUF by scragnogUpdated 2026-09-17
Download on Hugging Face
Parameters3.8B
Context24K
Layers28
Architectureyue2
Smallest quant0.0 GB
Quick answer

YuE2 LM needs about 3.9 GB of memory at Q4_K_M (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 20 quants, from 0.0 GB to 7.3 GB (BF16).

YuE2 LM – an open music generation model with 3.8B parameters

YuE2 LM is a 3.8B parameter music generation model that converts lyrics and style prompts into full songs. It supports editable scores and can run locally on a 24GB GPU without quantization. The model is licensed under CC BY-NC 4.0.

Good at

  • Text-to-music generation
  • Score editing and manipulation
  • Local inference on high‑VRAM GPUs

Limits

  • No vision support
  • Non‑commercial license only
  • Requires 24GB VRAM for full precision

Best for

  • Creating original songs from lyrics
  • Editing melodies and chords via score
  • Running local music generation without cloud

Who it’s for. Developers and musicians who need an open‑source music generation tool that can be run locally. The model is suitable for non‑commercial projects and research that require editable musical scores.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.4 GB
Fits Get file →
F320.5 GB 2.0 GB
Fits Get file →
F320.5 GB 2.0 GB
Fits Get file →
F161.2 GB 2.7 GB
Fits Get file →
F321.3 GB 2.7 GB
Fits Get file →
F161.4 GB 2.8 GB
Fits Get file →
IQ2_XS1.4 GB 2.8 GB
Fits Get file →
Q2_K1.7 GB 3.1 GB
Fits Get file →
IQ3_XXS1.7 GB 3.2 GB
Fits Get file →
Q3_K_S1.9 GB 3.4 GB
Fits Get file →
Q3_K_M2.1 GB 3.5 GB
Fits Get file →
IQ4_XS2.2 GB 3.7 GB
Fits Get file →
Q4_K_S2.3 GB 3.8 GB
Fits Get file →
MXFP42.4 GB 3.9 GB
Fits Get file →
Q4_K_M2.4 GB 3.9 GB
Fits Get file →
—2.5 GB 3.9 GB
Fits Get file →
Q5_K_M2.7 GB 4.2 GB
Fits Get file →
Q6_K3.1 GB 4.5 GB
Fits Get file →
Q8_03.9 GB 5.4 GB
Fits Get file →
BF167.3 GB 8.7 GB
Too big Get file →

For 8GB VRAM use Q4_K_S (file size 2.34GB, ~3.8GB memory). For 12GB VRAM use Q5_K_M (2.73GB, ~4.2GB). For 24GB VRAM use the full‑precision F32 (0.53GB, ~2GB).

What GPU do you need for YuE2 LM?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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 the main file (2.5 GB file, about 3.9 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.9 GB file, about 5.4 GB in use).
  • 12 GB VRAM: the best quant that fits is BF16 (7.3 GB file, about 8.7 GB in use).

Which YuE2 LM quant should you choose?

Q4_K_M is the usual starting point for YuE2 LM: it balances file size and quality well. Here it is a 2.4 GB file.

The Q8_0 file is 3.9 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureyue2
Parameters3.8B
Layers28
Trained context24,576 tokens
KV cache (fp16)112 KB per token

Source

Quantized byscragnog
FamilyYue
Base modelm-a-p/YuE2-3B
Downloads (HF)535,256
Last updated2026-09-17

Frequently asked questions about YuE2 LM

How much VRAM does YuE2 LM need?

About 3.9 GB at Q4_K_M with an 8K context window. That is the 2.4 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 LM on an 8 GB GPU?

Yes, with Q8_0: the 3.9 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of YuE2 LM GGUF?

It depends on the quant: file is 0.0 GB, F32 is 0.5 GB, F32 is 0.5 GB, F16 is 1.2 GB, F32 is 1.3 GB, F16 is 1.4 GB and 14 more.

What context length does YuE2 LM support?

The GGUF header lists a trained context length of 24,576 tokens (24K). The KV cache grows with the context you use: about 0.9 GB at 8K and 2.8 GB at 24K.

Where can I download YuE2 LM GGUF?

The files are on Hugging Face in the scragnog/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 LM 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 LM on 8 GB VRAM?

Yes, using the Q4_K_S quantized file which requires about 3.8GB of VRAM at 8k context.

Is YuE2 LM suitable for commercial use?

No, the model is licensed under CC BY-NC 4.0, which allows only non‑commercial use.

Does YuE2 LM support vision inputs?

No, the model does not support vision inputs.

Other GGUFs of YuE2-3B

Similar models

Browse all →

More from scragnog

All by scragnog →

More Yue models

All Yue →

Other small models

All small models →