DO

Dots.Mocr

DotsGGUF by prithivMLmodsUpdated 2026-08-28
Download on Hugging Face
Parameters1.78B
Context128K
Layers28
Architectureqwen2
Smallest quant0.9 GB
Quick answer

Dots.Mocr 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 11 quants, from 0.9 GB (Q3_K_S) to 3.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.9 GB.

Multimodal OCR model that parses documents and structured graphics into SVG

Dots.Mocr is a 1.78B parameter vision‑language model built on qwen2. It excels at document parsing, layout detection, and converting charts and UI layouts into SVG code. The model supports inference via llama.cpp and vLLM and is released under the MIT license.

Good at

  • Document parsing with high accuracy
  • Structured graphics to SVG conversion
  • Multimodal grounding and semantic understanding

Limits

  • No vision support beyond OCR tasks
  • Requires 8k context for memory estimates
  • No explicit language list provided

Best for

  • OCR of scanned documents
  • Converting charts to SVG for web use
  • Interactive document layout analysis

Who it’s for. Developers needing a lightweight OCR solution that also handles structured graphics. Researchers working on document understanding and layout parsing can use this model for both text extraction and visual element conversion.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S0.9 GB 1.6 GB
Fits Get file →
Q3_K_M0.9 GB 1.7 GB
Fits Get file →
Q3_K_L1.0 GB 1.7 GB
Fits Get file →
Q4_K_S1.1 GB 1.8 GB
Fits Get file →
Q4_K_M1.1 GB 1.9 GB
Fits Get file →
Q5_K_S1.3 GB 2.0 GB
Fits Get file →
Q5_K_M1.3 GB 2.0 GB
Fits Get file →
Q6_K1.5 GB 2.2 GB
Fits Get file →
Q8_01.9 GB 2.6 GB
Fits Get file →
BF163.6 GB 4.3 GB
Fits Get file →
F163.6 GB 4.3 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (1.12 GB file, ~1.9 GB memory). For 4 GB VRAM, Q3_K_S (0.86 GB file, ~1.6 GB memory). For higher precision, Q5_K_M (1.29 GB file, ~2 GB memory) is available but requires more memory.

What GPU do you need for Dots.Mocr?

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 BF16 (3.6 GB file, about 4.3 GB in use).

Which Dots.Mocr quant should you choose?

Q4_K_M is the usual starting point for Dots.Mocr: 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 Q3_K_S at 0.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2
Parameters1.78B
Layers28
Trained context131,072 tokens
KV cache (fp16)28 KB per token

Source

Quantized byprithivMLmods
FamilyDots
Licensemit
Downloads (HF)2,257
Last updated2026-08-28

Frequently asked questions about Dots.Mocr

How much VRAM does Dots.Mocr 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.Mocr on an 8 GB GPU?

Yes, with BF16: 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.Mocr GGUF?

It depends on the quant: Q3_K_S is 0.9 GB, Q3_K_M is 0.9 GB, Q3_K_L is 1.0 GB, Q4_K_S is 1.1 GB, Q4_K_M is 1.1 GB, Q5_K_S is 1.3 GB and 5 more.

What context length does Dots.Mocr 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.Mocr GGUF?

The files are on Hugging Face in the prithivMLmods/dots.mocr-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.Mocr 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.Mocr on 8 GB VRAM?

Yes, the Q4_K_M quantization uses about 1.9 GB of VRAM at 8k context, which fits within 8 GB.

Does Dots.Mocr support multiple languages?

The model supports multilingual document parsing across 100+ languages, though the language list is not specified in the card.

What is the context length for Dots.Mocr?

The model was trained with a context of 131072 tokens, but inference typically uses 8k context for memory estimates.

Other GGUFs of dots.mocr

Similar models

Browse all →

More from prithivMLmods

All by prithivMLmods →

More Dots models

All Dots →

Other tiny models

All tiny models →