rokot omr 2b needs about 3.3 GB of memory at Q8_0 (a 1.8 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.8 GB (Q8_0) to 3.4 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 3.8 GB.
rokot omr 2b – sheet music OCR model
rokot omr 2b is a fine‑tuned Qwen3‑VL‑2B‑Instruct model for converting printed sheet music into MusicXML via ABC notation. It processes one staff system at a time and outputs plain ABC text.
Good at
- Vision‑based music transcription
- Accurate ABC conversion
- Local deployment
Limits
- License cc‑by‑nc‑4.0
- Requires 262144 token context
- No video support
Best for
- Transcribing printed scores
- Generating MusicXML for DAWs
- Educational music tools
Who it’s for. Musicians, music educators, and developers who need a lightweight, local OCR for sheet music. The model runs on standard hardware and outputs text that can be fed into any ABC or MusicXML compatible software.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.8 GB | 3.3 GB | Fits | Get file → | |
| F16 | 3.4 GB | 4.9 GB | Fits | Get file → |
For 8 GB VRAM use Q8_0 (1.83 GB file, ~3.3 GB memory at 8 k context). For 12 GB VRAM use F16 (3.45 GB file, ~4.9 GB memory at 8 k context). Estimates are approximate.
What GPU do you need for rokot omr 2b?
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 Q8_0 (1.8 GB file, about 3.3 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.4 GB file, about 4.9 GB in use).
Which rokot omr 2b quant should you choose?
Q8_0 (1.8 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about rokot omr 2b
How much VRAM does rokot omr 2b need?
About 3.3 GB at Q8_0 with an 8K context window. That is the 1.8 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 rokot omr 2b on an 8 GB GPU?
Yes, with F16: the 3.4 GB file needs about 4.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of rokot omr 2b GGUF?
It depends on the quant: Q8_0 is 1.8 GB, F16 is 3.4 GB.
What context length does rokot omr 2b support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.9 GB at 8K and 3.8 GB at 32K.
Where can I download rokot omr 2b GGUF?
The files are on Hugging Face in the rokotmidi/rokot-omr-2b repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does rokot omr 2b 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 rokot omr 2b on 8 GB VRAM?
Yes, the Q8_0 quantized model uses about 3.3 GB of VRAM at 8 k context, fitting within an 8 GB GPU.
Does the model support video input?
No, rokot omr 2b is a vision‑language model designed for still images of sheet music, not video.
Is the model free to use?
It is licensed cc‑by‑nc‑4.0, so it can be used for non‑commercial purposes without fee.