Qianfan OCR is an open-source language model by baidu. Features: 4.7b LLM, VRAM: 9.5GB, License: apache-2.0, LLM Explorer Score: 0.41.
| LLM Name | Qianfan OCR |
| Repository 🤗 | https://huggingface.co/baidu/Qianfan-OCR |
| Model Size | 4.7b |
| Required VRAM | 9.5 GB |
| Updated | 2026-08-09 |
| Maintainer | baidu |
| Model Type | qianfan_ocr |
| Model Files | |
| Model Architecture | QianfanOCRForConditionalGeneration |
| License | apache-2.0 |
| Model Max Length | 1010000 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Torch Data Type | bfloat16 |
| Errors | replace |