YuE2 3B Ruach Studio IRA Merge needs about 4.8 GB of memory at Q8_0 (a 3.8 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 18 quants, from 2.9 GB (Q6_K) to 7.2 GB (BF16).
YuE2 3B Ruach Studio IRA Merge – 3.58B parameter music generation model
YuE2 3B Ruach Studio IRA Merge is a 3.58B parameter model built on the yue2 architecture. It incorporates the Instrumental and Real Audio LoRAs into the weights, enabling music generation with section plans and real‑production sound. The model is licensed under cc‑by‑nc‑4.0.
Good at
- Instrumental music with section plans
- Real‑production audio style
- Chain‑of‑thought score generation
Limits
- No vision support
- Requires 8k context for estimates
- License restricts commercial use
Best for
- Music production pipelines
- Educational music generation
- Creative songwriting tools
Who it’s for. Developers and musicians who want to generate instrumental music with structured sections and realistic audio on local hardware. The model is suitable for open‑source projects and non‑commercial research.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q6_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.8 GB | Fits | Get file → | |
| Q6_K | 2.9 GB | 3.8 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 → | |
| Q8_0 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q8_0 | 3.8 GB | 4.8 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 → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → | |
| BF16 | 7.2 GB | 8.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q6_K (2.94 GB file, ~3.8 GB memory at 8k context). For 12 GB VRAM, Q8_0 (3.81 GB file, ~4.8 GB memory). If higher precision is needed and 16 GB VRAM is available, BF16 (7.17 GB file, ~8.5 GB memory) can be used.
What GPU do you need for YuE2 3B Ruach Studio IRA Merge?
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 3B Ruach Studio IRA Merge quant should you choose?
Q8_0 (3.8 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 Q6_K at 2.9 GB, with the quality trade-offs that come with fewer bits. Very close to the original quality for most uses, at a clearly larger size than 4-bit.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about YuE2 3B Ruach Studio IRA Merge
How much VRAM does YuE2 3B Ruach Studio IRA Merge need?
About 4.8 GB at Q8_0 with an 8K context window. That is the 3.8 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 3B Ruach Studio IRA Merge 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 3B Ruach Studio IRA Merge GGUF?
It depends on the quant: Q6_K is 2.9 GB, Q6_K is 2.9 GB, Q6_K is 2.9 GB, Q6_K is 2.9 GB, Q6_K is 2.9 GB, Q6_K is 2.9 GB and 12 more.
Where can I download YuE2 3B Ruach Studio IRA Merge GGUF?
The files are on Hugging Face in the goldhub/YuE2-3B-Ruach_Studio-IRA-Merge 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 3B Ruach Studio IRA Merge 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 this model on 8 GB VRAM?
Yes, the Q6_K quantization requires about 3.8 GB of VRAM at 8k context, which fits within an 8 GB budget.
Does the model support image inputs?
No, the model has no vision capability and only processes text and music tokens.
Is the model free for commercial use?
No, the cc‑by‑nc‑4.0 license prohibits commercial use without permission.