dots.ocr needs about 2.6 GB of memory at Q8_0 (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.9 GB (Q8_0) to 3.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Multilingual document layout parsing in a single vision‑language model
dots.ocr is a 1.8 B‑parameter vision‑language model that unifies layout detection and content recognition. It supports multilingual document parsing and maintains good reading order. The model is licensed under MIT and can be run with llama.cpp.
Good at
- Vision‑language document parsing
- Multilingual layout detection
- Fast inference on small models
Limits
- No vision support beyond document parsing
- Large VRAM requirement for higher context
- No explicit language list provided
Best for
- Parsing scanned PDFs
- Extracting tables and formulas
- Automating document workflows
Who it’s for. Developers needing a lightweight, multilingual document parser that runs locally. The model is suitable for applications that require both layout and content extraction from images.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| F16 | 3.6 GB | 4.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q8_0 (1.89 GB file, ~2.6 GB memory at 8 k context). For 12 GB VRAM, F16 (3.56 GB file, ~4.3 GB memory at 8 k context) is available. Memory estimates are approximate.
What GPU do you need for dots.ocr?
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 (1.9 GB file, about 2.6 GB in use).
- 6 GB VRAM: the best quant that fits is F16 (3.6 GB file, about 4.3 GB in use).
Which dots.ocr quant should you choose?
Q8_0 (1.9 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 dots.ocr
How much VRAM does dots.ocr need?
About 2.6 GB at Q8_0 with an 8K context window. That is the 1.9 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 dots.ocr on an 8 GB GPU?
Yes, with F16: the 3.6 GB file needs about 4.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of dots.ocr GGUF?
It depends on the quant: Q8_0 is 1.9 GB, F16 is 3.6 GB.
What context length does dots.ocr support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.9 GB at 32K.
Where can I download dots.ocr GGUF?
The files are on Hugging Face in the ggml-org/dots.ocr-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 dots.ocr use?
Hugging Face lists the license as mit. 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 dots.ocr on 8 GB VRAM?
Yes, the Q8_0 quantized model requires about 2.6 GB of VRAM at 8 k context, fitting within an 8 GB budget.
Does dots.ocr support multiple languages?
Yes, it is a multilingual model, though the specific languages are not listed in the provided data.
Is there a vision‑language version of dots.ocr?
Yes, the model includes vision capabilities for document layout parsing, as indicated by its detected abilities.