Next Ocr needs about 10.4 GB of memory at Q8_0 (a 8.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.
Next OCR 8B – Compact OCR AI with math and table understanding
Next OCR 8B is an 8‑billion parameter model optimized for optical character recognition. It handles multilingual documents and extracts structured content such as tables, forms, and formulas. The model is instruction‑tuned for document analysis.
Good at
- Accurate OCR with math and tables
- Multilingual document extraction
- Fast inference on moderate hardware
Limits
- Requires ~10.4GB VRAM at 8k context
- No vision support beyond OCR
- Apache‑2.0 license
Best for
- Document digitization
- Invoice and receipt processing
- Multilingual OCR pipelines
Who it’s for. Developers building OCR solutions that need accurate text extraction, including mathematical and tabular data, across many languages. Suitable for enterprise document management and automated data capture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.7 GB | 10.4 GB | Too big | Get file → |
The only available quant is Q8_0 with a file size of 8.71GB. It requires approximately 10.4GB of VRAM at 8k context. For systems with 12GB or more VRAM, Q8_0 is recommended. No smaller quant is provided.
What GPU do you need for Next Ocr?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (8.7 GB file, about 10.4 GB in use).
Which Next Ocr quant should you choose?
Q8_0 (8.7 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 Next Ocr
How much VRAM does Next Ocr need?
About 10.4 GB at Q8_0 with an 8K context window. That is the 8.7 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 Next Ocr on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Next Ocr GGUF?
It depends on the quant: Q8_0 is 8.7 GB.
What context length does Next Ocr support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.
Where can I download Next Ocr GGUF?
The files are on Hugging Face in the thelamapi/next-ocr repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Next Ocr 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 Next OCR on 8GB VRAM?
No, the model needs about 10.4GB of VRAM at 8k context, so 8GB is insufficient.
Does Next OCR support vision tasks beyond OCR?
No, the model is designed specifically for OCR and does not support general vision tasks.
Which languages does Next OCR support?
It supports over 30 languages, including Turkish, English, German, Spanish, French, Chinese, Japanese, Korean, and Russian.