All tasks / Models
HPD-Parsing
PaddlePaddle's 1B open-weights document-parsing VLM built on InternVL3.5-1B, separate from PaddleOCR-VL.
- Baidu (PaddlePaddle)
- Open weights
- Released 21 Jul 2026
Where it ranks
- –Documents & OCRModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Baidu (PaddlePaddle)
- Family
- HPD-Parsing
- Released
- 21 Jul 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 1.07B
- GPU memory to run locally
- ~4 GB (Estimate, no official figure: BF16 weights ≈ 1.07 B × 2 GB + ~1.5 GB runtime overhead. Size is the Hugging Face safetensors total.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from huggingface.co, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| ParseBench (models) | 54% | HPD-ParsingOverall (mean of tables, charts, content faithfulness, semantic formatting, visual grounding) from leaderboard.csv in the ParseBench repo (last leaderboard commit 2026-10-09). | 9 Oct 2026 | github.com |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.