MI

MiniCPM-OCR-1.0

MiniCPMGGUF by AtomicChatUpdated 2026-10-28
Download on Hugging Face
Parameters752M
Context256K
Layers24
Architectureqwen35
Smallest quant0.5 GB
Quick answer

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 4 quants, from 0.5 GB (Q4_K_M) to 0.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

MiniCPM-OCR-1.0: 1.3B OCR model for text, tables, formulas, charts, and seals

MiniCPM-OCR-1.0 is a 1.3B parameter OCR model based on the qwen35 architecture. It excels at document understanding, handling Chinese and English images, PDFs, scans, and photographs. The model supports reasoning, tools, and vision capabilities.

Good at

  • OCR on mixed-language documents
  • Table and formula extraction
  • Fast inference with GGUF

Limits

  • No vision support in llama.cpp without the Q8_0 projector
  • Requires 8k context for memory estimates
  • License is apache-2.0

Best for

  • Document digitization workflows
  • Automated data extraction from PDFs
  • OCR in low‑resource environments

Who it’s for. Developers building OCR pipelines who need a lightweight, open‑source model with strong text and table extraction. The model is suitable for integration into web services, desktop applications, or embedded systems that can run GGUF files.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.5 GB 1.4 GB
Fits Get file →
Q5_K_M0.6 GB 1.5 GB
Fits Get file →
Q6_K0.7 GB 1.6 GB
Fits Get file →
Q8_00.8 GB 1.7 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.53 GB, ~1.4 GB VRAM at 8k context) or Q5_K_M (0.59 GB, ~1.5 GB). If 12 GB VRAM is available, Q6_K (0.73 GB, ~1.6 GB) offers higher quality. Q8_0 (0.81 GB, ~1.7 GB) gives the best precision but needs the most memory.

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 Q8_0 (0.8 GB file, about 1.7 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters752M
Layers24
Trained context262,144 tokens
KV cache (fp16)48 KB per token

Source

Quantized byAtomicChat
FamilyMiniCPM
Licenseapache-2.0
Downloads (HF)1,279
Last updated2026-10-28

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 Q8_0: the 0.8 GB file needs about 1.7 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: Q4_K_M is 0.5 GB, Q5_K_M is 0.6 GB, Q6_K is 0.7 GB, Q8_0 is 0.8 GB.

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 AtomicChat/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, the Q4_K_M or Q5_K_M quantized files fit within 8 GB VRAM, using approximately 1.4–1.5 GB at 8k context.

Does the model support vision in llama.cpp?

Vision support requires the Q8_0 projector; without it, llama.cpp can only run the text model.

What license applies to this model?

The model is released under the apache-2.0 license, allowing commercial and non‑commercial use.

Other GGUFs of MiniCPM-OCR-1.0

Similar models

Browse all →

More from AtomicChat

All by AtomicChat →

More MiniCPM models

All MiniCPM →

Other tiny models

All tiny models →