MiniCPM-OCR 1.0 DSpark needs about 0.8 GB of memory at Q4_K_M (a 0.2 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.2 GB (Q4_0) to 0.6 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 0.3 GB.
MiniCPM‑OCR 1.0 DSpark – OCR‑focused model in GGUF format
MiniCPM‑OCR 1.0 DSpark is a draft GGUF build of the MiniCPM‑OCR 1.0 model. It is designed for text‑centric document understanding, including tables, formulas, charts, and structured extraction. The model supports multimodal input and can be paired with the main checkpoint for full OCR capability.
Good at
- OCR document parsing
- Table and formula extraction
- Multimodal text recognition
Limits
- Draft only, requires main checkpoint
- No vision support in draft
- Limited to 262144 context tokens
Best for
- Document parsing pipelines
- Structured data extraction
- OCR‑based automation
Who it’s for. Developers building OCR solutions who need a lightweight, quantizable model. The draft version is suitable for testing and integration with the main MiniCPM‑OCR 1.0 checkpoint.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q4_1 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q5_0 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q5_K_S | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q5_K_M | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q5_1 | 0.2 GB | 0.8 GB | Fits | Get file → | |
| Q6_K | 0.3 GB | 0.8 GB | Fits | Get file → | |
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.2 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_0, Q4_K_S, or Q4_K_M (0.21 GB file, ~0.8 GB memory). For 16 GB VRAM, Q6_K (0.26 GB file, ~0.8 GB memory) or Q8_0 (0.33 GB file, ~0.9 GB memory) provide higher precision. F16 (0.61 GB file, ~1.2 GB memory) requires larger GPU memory.
What GPU do you need for MiniCPM-OCR 1.0 DSpark?
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 F16 (0.6 GB file, about 1.2 GB in use).
Which MiniCPM-OCR 1.0 DSpark quant should you choose?
Q4_K_M is the usual starting point for MiniCPM-OCR 1.0 DSpark: it balances file size and quality well. Here it is a 0.2 GB file.
The Q8_0 file is 0.3 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 Q4_0 at 0.2 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about MiniCPM-OCR 1.0 DSpark
How much VRAM does MiniCPM-OCR 1.0 DSpark need?
About 0.8 GB at Q4_K_M with an 8K context window. That is the 0.2 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 DSpark on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.2 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 DSpark GGUF?
It depends on the quant: Q4_0 is 0.2 GB, Q4_K_S is 0.2 GB, Q4_K_M is 0.2 GB, Q4_1 is 0.2 GB, Q5_0 is 0.2 GB, Q5_K_S is 0.2 GB and 5 more.
What context length does MiniCPM-OCR 1.0 DSpark support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 32K.
Where can I download MiniCPM-OCR 1.0 DSpark GGUF?
The files are on Hugging Face in the openbmb/MiniCPM-OCR-1.0-DSpark-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 DSpark 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 DSpark on 8 GB VRAM?
Yes, use Q4_0, Q4_K_S, or Q4_K_M quantizations; each requires about 0.8 GB memory at 8k context.
Does the draft model support vision input?
The draft model itself does not provide vision support; it must be paired with the main checkpoint for multimodal input.
What license applies to this model?
The model is released under the apache-2.0 license.