prithivMLmods / WeVisDoc-2B-GGUF

huggingface.co
Total runs: 2.3K
24-hour runs: 0
7-day runs: 1.3K
30-day runs: 1.9K
Model's Last Updated: September 18 2026
image-text-to-text

Introduction of WeVisDoc-2B-GGUF

Model Details of WeVisDoc-2B-GGUF

WeVisDoc-2B-GGUF

WeVisDoc-2B is a compact end-to-end document parsing model developed by Tencent that converts page images directly into structured Markdown output, complete with LaTeX-formatted formulas and HTML tables. Fine-tuned from Qwen3-VL-2B-Instruct, it is purpose-built for document parsing rather than general vision-language tasks, and supports both English and Chinese. Despite its small 2B-parameter size, it delivers near state-of-the-art results, scoring 95.06 Overall on OmniDocBench v1.6—second only to its larger 4B sibling (95.38) and ahead of much bigger models like olmOCR-2-7B, dots.mocr, and Logics-Parsing-v2—while on PureDocBench it achieves a mean Overall score of 73.86 across the three tracks (79.36 Clean, 76.62 Digital Degraded, 65.60 Real Degraded), leading the Clean and Digital Degraded settings among compared parsers. Released under the Apache 2.0 license, it can be served via vLLM (requiring vLLM ≥0.11.1) or run locally with Transformers, and uses the same client tooling as the 4B variant, making it an attractive option for resource-constrained deployments that still require top-tier parsing accuracy.

Model Files
File Name Quant Type File Size File Link
WeVisDoc-2B.BF16.gguf BF16 4.07 GB Download
WeVisDoc-2B.F16.gguf F16 4.07 GB Download
WeVisDoc-2B.Q3_K_L.gguf Q3_K_L 1.14 GB Download
WeVisDoc-2B.Q3_K_M.gguf Q3_K_M 1.07 GB Download
WeVisDoc-2B.Q4_K_M.gguf Q4_K_M 1.28 GB Download
WeVisDoc-2B.Q4_K_S.gguf Q4_K_S 1.24 GB Download
WeVisDoc-2B.Q5_K_M.gguf Q5_K_M 1.47 GB Download
WeVisDoc-2B.Q5_K_S.gguf Q5_K_S 1.44 GB Download
WeVisDoc-2B.Q6_K.gguf Q6_K 1.67 GB Download
WeVisDoc-2B.Q8_0.gguf Q8_0 2.17 GB Download
WeVisDoc-2B.mmproj-bf16.gguf mmproj-bf16 823 MB Download
WeVisDoc-2B.mmproj-f16.gguf mmproj-f16 823 MB Download
WeVisDoc-2B.mmproj-q8_0.gguf mmproj-q8_0 445 MB Download
llama.cpp

LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp

Runs of prithivMLmods WeVisDoc-2B-GGUF on huggingface.co

2.3K
Total runs
0
24-hour runs
71
3-day runs
1.3K
7-day runs
1.9K
30-day runs

More Information About WeVisDoc-2B-GGUF huggingface.co Model

More WeVisDoc-2B-GGUF license Visit here:

https://choosealicense.com/licenses/apache-2.0

WeVisDoc-2B-GGUF huggingface.co

WeVisDoc-2B-GGUF huggingface.co is an AI model on huggingface.co that provides WeVisDoc-2B-GGUF's model effect (), which can be used instantly with this prithivMLmods WeVisDoc-2B-GGUF model. huggingface.co supports a free trial of the WeVisDoc-2B-GGUF model, and also provides paid use of the WeVisDoc-2B-GGUF. Support call WeVisDoc-2B-GGUF model through api, including Node.js, Python, http.

prithivMLmods WeVisDoc-2B-GGUF online free

WeVisDoc-2B-GGUF huggingface.co is an online trial and call api platform, which integrates WeVisDoc-2B-GGUF's modeling effects, including api services, and provides a free online trial of WeVisDoc-2B-GGUF, you can try WeVisDoc-2B-GGUF online for free by clicking the link below.

prithivMLmods WeVisDoc-2B-GGUF online free url in huggingface.co:

https://huggingface.co/prithivMLmods/WeVisDoc-2B-GGUF

WeVisDoc-2B-GGUF install

WeVisDoc-2B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find WeVisDoc-2B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of WeVisDoc-2B-GGUF install, users can directly use WeVisDoc-2B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

WeVisDoc-2B-GGUF install url in huggingface.co:

https://huggingface.co/prithivMLmods/WeVisDoc-2B-GGUF

Url of WeVisDoc-2B-GGUF

Provider of WeVisDoc-2B-GGUF huggingface.co

prithivMLmods
ORGANIZATIONS

Other API from prithivMLmods