Model reference · open weights
Qianfan-OCR is an open-weight language model from baidu, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
🤖 Demo | 📄 Technical Report | 🖥️ Qianfan Platform | 💻 GitHub | 🧩 Skill Introduction Qianfan-OCR is a 4B-parameter end-to-end document intelligence model developed by the Baidu Qianfan Team. It unifies document parsing, layout analysis, and document understanding within a single vision-language architecture. Unlike traditional multi-stage OCR pipelines that chain separate layout detection, text recognition, and language comprehension modules, Qianfan-OCR performs direct image-to-Markdown conversion and supports a broad range of prompt-driven tasks — from structured document parsing and table extraction to chart understanding, document question answering, and key information extraction — all within one model. Key Highlights - 🏆 #1 End-to-End Model on OmniDocBench v1.5 — Achieves 93.12 overall score, surpassing DeepSeek-OCR-v2 (91.09), Gemini-3 Pro (90.33), and all other end-to-end models - 🏆 #1 End-to-End Model on OlmOCR Bench — Scores 79.8 - 🏆 #1 on Key Information Extraction — Overall mean score of 87.9 across five public KIE benchmarks, surpassing Gemini-3.1-Pro, Gemini-3-Pro, Seed-2.0, and Qwen3-VL-235B-A22B - 🧠 Layout-as-Thought — An innovative optional thinking phase that recovers explicit layout analysis within the end-to-end paradigm via ⟨think⟩ tokens - 🌍 192 Languages — Multilingual OCR support across diverse scripts - ⚡ Efficient Deployment — Achieves 1.024 PPS (pages per second) with W8A8 quantization on a single A100 GPU Architecture Qianfan-OCR adopts the multimodal bridging architecture from Qianfan-VL, consisting of three core components: Layout-as-Thought A key innovation is Layout-as-Thought: an optional thinking phase triggered by ⟨think⟩ tokens, where the model generates structured layout representations (bounding boxes, element types, reading order) before producing final outputs. This mechanism serves two purposes: 1. Functional: Recovers layout analysis capability within the end-to-end paradigm — users obtain structured layout results directly 2. Enhancement: Provides targeted accuracy improvements on documents with complex layouts, cluttered elements, or non-standard reading orders When to use: Enable thinking for heterogeneous pages with m
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | baidu |
|---|---|
| Type | Language models |
| Parameters (lead) | 4.7B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-03-18 |
| Popularity | 77k downloads / month |
| Likes | 1,203 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| Qianfan-OCR | 4.7B | BF16 | ~10.9 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Document Parsing | OmniDocBench v1.5 | Overall Score | 93.12 |
| OCR | OlmOCR Bench | Overall Score | 79.8 |
| OCR | OCRBench | Score | 880 |
Using it via the API
Once AxForge deploys qianfan-ocr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (qianfan-ocr below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qianfan-ocr","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗