Dots.Ocr needs about 1.9 GB of memory at Q4_K_M (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 12 quants, from 0.8 GB (Q2_K) to 3.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.
Dots.Ocr – a 1.78B vision‑language model for multilingual document parsing
Dots.Ocr is a 1.78B‑parameter model based on qwen2. It performs layout detection, content recognition, and formula recognition in a single pass. The model supports vision and coding tasks and is released under the MIT license.
Good at
- Multilingual document layout parsing
- Vision‑language inference
- Fast inference on small GPUs
Limits
- No dedicated vision support beyond the base model
- Requires 8k context for full memory estimates
- No explicit vision‑only mode
Best for
- Parsing scanned PDFs
- Extracting tables from documents
- OCR for low‑resource languages
Who it’s for. Developers needing a compact vision‑language model for document analysis. Researchers working on multilingual OCR pipelines may also benefit.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.8 GB | 1.5 GB | Fits | Get file → | |
| Q3_K_S | 0.9 GB | 1.6 GB | Fits | Get file → | |
| Q3_K_M | 0.9 GB | 1.7 GB | Fits | Get file → | |
| Q3_K_L | 1.0 GB | 1.7 GB | Fits | Get file → | |
| IQ4_XS | 1.0 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_S | 1.1 GB | 1.8 GB | Fits | Get file → | |
| Q4_K_M | 1.1 GB | 1.9 GB | Fits | Get file → | |
| Q5_K_S | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q5_K_M | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q6_K | 1.5 GB | 2.2 GB | Fits | Get file → | |
| 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 Q4_K_M (1.12 GB file, ~1.9 GB memory). For 12 GB VRAM, Q5_K_M (1.29 GB file, ~2 GB memory) is suitable. If more memory is available, Q8_0 (1.89 GB file, ~2.6 GB memory) offers higher precision.
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?
Q4_K_M is the usual starting point for Dots.Ocr: it balances file size and quality well. Here it is a 1.1 GB file.
The Q8_0 file is 1.9 GB, about 1.7 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 Q2_K at 0.8 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
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 1.9 GB at Q4_K_M with an 8K context window. That is the 1.1 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: Q2_K is 0.8 GB, Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, IQ4_XS is 1.0 GB, Q4_K_S is 1.1 GB and 6 more.
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 mradermacher/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 Q4_K_M quant uses about 1.9 GB memory at 8k context, fitting within 8 GB VRAM.
Does Dots.Ocr support vision tasks?
Yes, it includes vision capabilities for layout and content recognition.
What license is Dots.Ocr released under?
The model is released under the MIT license.