MiniCPM OCR 1.0 needs about 1.4 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 9 quants, from 0.5 GB (Q3_K_M) to 1.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
MiniCPM OCR 1.0 – 1.3B vision‑language OCR model
MiniCPM OCR 1.0 is a 1.3B‑parameter vision‑language model for Chinese and English document parsing. It extracts text, tables, formulas, charts, and seals from scans, skewed pages, and photos. The model is open‑weight under Apache‑2.0 and supports inference via llama.cpp, vLLM, SGLang, and Ollama.
Good at
- OCR of Chinese and English documents
- Structured key information extraction
- Fast inference with DSpark acceleration
Limits
- No vision support beyond OCR
- Requires 8k context for full capability
- No external vision libraries needed
Best for
- Document digitization pipelines
- Automated form extraction
- OCR‑based data entry
Who it’s for. Developers building OCR solutions that need high accuracy on Chinese and English documents. The model is suitable for applications requiring structured output such as tables to HTML or formulas to LaTeX.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q3_K_L | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.4 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q6_K | 0.6 GB | 1.5 GB | Fits | Get file → | |
| Q8_0 | 0.8 GB | 1.7 GB | Fits | Get file → | |
| BF16 | 1.5 GB | 2.4 GB | Fits | Get file → |
For 8 GB VRAM, Q3_K_M (0.47 GB) or Q4_K_M (0.53 GB) are suitable, using about 1.4 GB of VRAM at 8k context. For 16 GB VRAM, Q5_K_M (0.58 GB) or Q6_K (0.63 GB) provide higher precision with ~1.5 GB VRAM usage. BF16 (1.52 GB) needs ~2.4 GB VRAM and offers the highest quality.
What GPU do you need for MiniCPM OCR 1.0?
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 BF16 (1.5 GB file, about 2.4 GB in use).
Which MiniCPM OCR 1.0 quant should you choose?
Q4_K_M is the usual starting point for MiniCPM OCR 1.0: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.8 GB, about 1.5 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_M at 0.5 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
Source
Frequently asked questions about MiniCPM OCR 1.0
How much VRAM does MiniCPM OCR 1.0 need?
About 1.4 GB at Q4_K_M with an 8K context window. That is the 0.5 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 MiniCPM OCR 1.0 on an 8 GB GPU?
Yes, with BF16: the 1.5 GB file needs about 2.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MiniCPM OCR 1.0 GGUF?
It depends on the quant: Q3_K_M is 0.5 GB, Q3_K_L is 0.5 GB, Q4_K_S is 0.5 GB, Q4_K_M is 0.5 GB, Q5_K_S is 0.6 GB, Q5_K_M is 0.6 GB and 3 more.
What context length does MiniCPM OCR 1.0 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download MiniCPM OCR 1.0 GGUF?
The files are on Hugging Face in the prithivMLmods/MiniCPM-OCR-1.0-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 MiniCPM OCR 1.0 use?
Hugging Face lists the license as apache-2.0. 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 MiniCPM OCR 1.0 on 8 GB VRAM?
Yes, use Q3_K_M or Q4_K_M quantizations; each uses about 1.4 GB VRAM at 8k context.
Does the model support PDF input?
Yes, it can process PDFs, including scans, curved pages, and photographs.
Is the model licensed for commercial use?
It is released under Apache‑2.0, which allows commercial deployment.