DeepSeek OCR needs about 4.0 GB of memory at Q8_0 (a 3.1 GB file) with an 8K context window, so it fits on a 4 GB GPU.
DeepSeek OCR – 2.93 B parameter OCR model in GGUF format
DeepSeek OCR is a 2.93 B parameter model designed for optical character recognition tasks. It is available as a single Q8_0 quantized GGUF file. The model is lightweight enough for local inference with modest VRAM.
Good at
- OCR on printed text
- OCR on scanned documents
- OCR on low‑resolution images
Limits
- No vision support beyond OCR
- Requires 8 k context for full operation
- No license information provided
Best for
- Document digitization
- Text extraction from PDFs
- Batch OCR processing
Who it’s for. Users needing a dedicated OCR model for local inference. Suitable for developers building document processing pipelines or researchers testing OCR performance.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 3.1 GB | 4.0 GB | Fits | Get file → |
The only available quant is Q8_0, file size 3.13 GB. It requires approximately 4 GB of VRAM at 8 k context. This is the recommended quant for any deployment with at least 4 GB VRAM.
What GPU do you need for DeepSeek OCR?
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 Q8_0 (3.1 GB file, about 4.0 GB in use).
Which DeepSeek OCR quant should you choose?
Q8_0 (3.1 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 DeepSeek OCR
How much VRAM does DeepSeek OCR need?
About 4.0 GB at Q8_0 with an 8K context window. That is the 3.1 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 DeepSeek OCR on an 8 GB GPU?
Yes, with Q8_0: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek OCR GGUF?
It depends on the quant: Q8_0 is 3.1 GB.
Where can I download DeepSeek OCR GGUF?
The files are on Hugging Face in the ggml-org/DeepSeek-OCR-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run DeepSeek OCR on 4 GB VRAM?
Yes, the Q8_0 quant requires about 4 GB of VRAM at 8 k context, which matches a 4 GB VRAM budget.
Does DeepSeek OCR support multiple languages?
The model does not list supported languages; no language information is provided.
Is there a license for using DeepSeek OCR?
No license information is included in the model metadata.