All tasks / Models
Qianfan-OCR
Baidu's 4B open-weights OCR VLM for end-to-end document parsing into Markdown.
- Baidu
- Open weights
- Released 18 Mar 2026
Where it ranks
- SDocuments & OCRModels · Local · 94 on OmniDocBench v1.6 (end-to-end, v1.6_full)
Facts
- Vendor
- Baidu
- Family
- Qianfan-OCR
- Released
- 18 Mar 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 4.74B
- GPU memory to run locally
- ~11 GB (Estimate, no official figure: BF16 weights ≈ 4.74 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 |
|---|---|---|---|---|
| OmniDocBench v1.6 (end-to-end, v1.6_full) | 94 | Qianfan-OCROverall score in the README's end-to-end table 'OmniDocBench (v1.6_full)' (last leaderboard update 2026-09-11). | 11 Sep 2026 | github.com |
| ParseBench (models) | 46.2% | Qianfan-OCROverall (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.