All tasks / Models
HunyuanOCR-1.5
Tencent's ~1B open-weights OCR VLM for document parsing, text spotting, information extraction and image translation.
- Tencent (Hunyuan)
- Open weights
Where it ranks
- –Documents & OCRModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- Tencent (Hunyuan)
- Family
- HunyuanOCR
- Released
- —
- Weights
- Open: download and run it yourself
- License
- Tencent Hunyuan Community License
- Parameters
- 1.12B
- GPU memory to run locally
- ~4 GB (Estimate, no official figure: BF16 weights ≈ 1.12 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 |
|---|---|---|---|---|
| MDPBench (multilingual document parsing) | 76.8% | HunyuanOCR-1.5Overall (public split, page-level mean of text, formula and table scores) from the board's leaderboard.json (updated 2026-10-04). | 4 Oct 2026 | huggingface.co |
| ParseBench (models) | 63.9% | HunyuanOCR 1.5Overall (mean of tables, charts, content faithfulness, semantic formatting, visual grounding) from leaderboard.csv in the ParseBench repo (last leaderboard commit 2026-10-09). OmniDocBench's 'HunyuanOCR' row (89.95) is the 1.0 version and is not recorded. | 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.
Earlier versions
- HunyuanOCR-1.0 · 18 Nov 2025