SheetSage2 needs about 3.5 GB of memory at its main file (a 2.7 GB file) with an 8K context window, so it fits on a 4 GB GPU.
SheetSage2 transcribes music recordings into editable lead sheets and musical annotations
SheetSage2 converts audio into melody, chords, beats, key, structure, and editable scores. It outputs MIDI parts, annotation text, and optional tensors for embeddings and logits. The GGUF file contains the full merged model, no separate backbone needed.
Good at
- Transcribing complete songs into lead sheets
- Generating editable ABC or MIDI
- Providing embeddings and token predictions
Limits
- No vision support
- Requires 8.0k context for full operation
- License is cc‑by‑nc‑4.0
Best for
- Music transcription workflows
- Score editing tools
- Embedding extraction for custom applications
Who it’s for. Developers and musicians who need automated lead‑sheet generation from audio. The model is suitable for integration into music production pipelines or research projects requiring structured musical outputs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.7 GB | 3.5 GB | Fits | Get file → |
The available GGUF file is 2.71 GB and requires approximately 3.5 GB of VRAM at 8 k context. For systems with 8 GB VRAM, the default quant is suitable. No other quant variants are provided.
What GPU do you need for SheetSage2?
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 the main file (2.7 GB file, about 3.5 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SheetSage2
How much VRAM does SheetSage2 need?
About 3.5 GB at its main file with an 8K context window. That is the 2.7 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 SheetSage2 on an 8 GB GPU?
Yes, with the smaller files: the 2.7 GB file needs about 3.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SheetSage2 GGUF?
It depends on the quant: file is 2.7 GB.
Where can I download SheetSage2 GGUF?
The files are on Hugging Face in the audio-cpp/SheetSage2-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 SheetSage2 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 SheetSage2 on 8 GB VRAM?
Yes, the 2.71 GB GGUF file requires about 3.5 GB VRAM at 8 k context, which fits within 8 GB.
Does SheetSage2 support vision tasks?
No, the model only processes audio and outputs musical annotations.
What license applies to SheetSage2?
The model is licensed under cc‑by‑nc‑4.0, allowing non‑commercial use with attribution.