This repository contains GGUF format quantizations of
OvisOCR2
, a compact 0.8B end-to-end model for page-level document parsing. The original model was developed by
ATH-MaaS
by post-training
Qwen3.5-0.8B
to parse full document pages directly into clean Markdown (including LaTeX formulas, HTML tables, and layout components).
OvisOCR2 establishes a new state-of-the-art for compact document understanding, scoring
96.58
on OmniDocBench v1.6 and outperforming traditional, multi-stage layout analysis pipelines.
Available Files
Main Text Models
File Name
Precision / Quantization
File Size
Description
OvisOCR2-F16.gguf
16-bit Float
1.52 GB
Baseline unquantized model
OvisOCR2-BF16.gguf
16-bit Brain Float
1.52 GB
Native weight precision
OvisOCR2-Q8_0.gguf
8-bit
812 MB
Near-identical precision to F16
OvisOCR2-Q6_K.gguf
6-bit
630 MB
Excellent balance of size and accuracy
OvisOCR2-Q5_K_M.gguf
5-bit (Medium)
578 MB
Recommended for low-resource deployment
OvisOCR2-Q5_K_S.gguf
5-bit (Small)
564 MB
Highly optimized 5-bit layout
OvisOCR2-Q4_K_M.gguf
4-bit (Medium)
529 MB
Standard 4-bit quantization
OvisOCR2-Q4_K_S.gguf
4-bit (Small)
505 MB
Lightweight 4-bit footprint
OvisOCR2-Q3_K_M.gguf
3-bit (Medium)
466 MB
Maximum compression ratio
Multimodal Projectors (
mmproj
)
Note: Because OvisOCR2 is a vision-language model, you
must
download one of these image processing units alongside your choice of the text models listed above.
mmproj-F32.gguf
(402 MB) - Unquantized full precision projector.
mmproj-F16.gguf
(205 MB) - Recommended standard performance/size option.
mmproj-BF16.gguf
(207 MB) - Target alternative precision layout.
Inference Guide (
llama.cpp
)
To run multimodal OCR tasks using these GGUF files, you need to use the
llama-minicpmv-cli
or
llama-llava-cli
tool (depending on your build version of
llama.cpp
) to handle simultaneous image and text tokens.
Basic Command Line Example
# Run parsing via llama.cpp cli tools
./llama-minicpmv-cli \
-m OvisOCR2-Q5_K_M.gguf \
--mmproj mmproj-F16.gguf \
--image /path/to/your/document_page.jpg \
-p "<|im_start|>user\nExtract all readable content from the image in natural human reading order and output the result as a single Markdown document. Format formulas as LaTeX. Format tables as HTML: <table>...</table>. Preserve the original text without translation.<|im_end|>\n<|im_start|>assistant\n" \
-n 4096 \
--temp 0.0
Runs of Abiray OvisOCR2-GGUF on huggingface.co
6.4K
Total runs
-48
24-hour runs
-130
3-day runs
-864
7-day runs
-9.2K
30-day runs
More Information About OvisOCR2-GGUF huggingface.co Model
OvisOCR2-GGUF huggingface.co is an AI model on huggingface.co that provides OvisOCR2-GGUF's model effect (), which can be used instantly with this Abiray OvisOCR2-GGUF model. huggingface.co supports a free trial of the OvisOCR2-GGUF model, and also provides paid use of the OvisOCR2-GGUF. Support call OvisOCR2-GGUF model through api, including Node.js, Python, http.
OvisOCR2-GGUF huggingface.co is an online trial and call api platform, which integrates OvisOCR2-GGUF's modeling effects, including api services, and provides a free online trial of OvisOCR2-GGUF, you can try OvisOCR2-GGUF online for free by clicking the link below.
Abiray OvisOCR2-GGUF online free url in huggingface.co:
OvisOCR2-GGUF is an open source model from GitHub that offers a free installation service, and any user can find OvisOCR2-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of OvisOCR2-GGUF install, users can directly use OvisOCR2-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.