Model reference · open weights
PP-OCRv6_medium_det is an open-weight language model from PaddlePaddle, 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
PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks [](https://github.com/PaddlePaddle/PaddleOCR) [](https://huggingface.co/PaddlePaddle/PP-OCRv6mediumdet) [](https://x.com/PaddlePaddle) [](./LICENSE) [](https://huggingface.co/PaddlePaddle/PP-OCRv6mediumdetsafetensors) [](https://huggingface.co/PaddlePaddle/PP-OCRv6mediumdetonnx) 🔥 Official Website 📝 Technical Report PP-OCRv6 Overview PP-OCRv6 is a lightweight OCR system that combines architectural innovation with data-centric optimization. It redesigns the backbone, detection neck, and recognition neck around a unified MetaFormer-style building block with structural reparameterization. Three model tiers (medium, small, tiny) share the same block primitives, covering deployment scenarios from server to edge. Key Features 1. Unified and Scalable Model Family: A three-tier OCR model family spanning 1.5M to 34.5M parameters. PP-OCRv6medium achieves 86.2% detection Hmean and 83.2% recognition accuracy, outperforming PP-OCRv5server by +4.6% and +5.1% respectively. 2. Lightweight Architectural Innovations: (i) LCNetV4, a MetaFormer-style lightweight backbone with structural reparameterization; (ii) RepLKFPN, a detection neck with dilated reparameterizable depthwise convolutions; (iii) EncoderWithLightSVTR, a recognition neck with local-global attention and additive skip connections. 3. Multi-Language and Scenario Support: Supports 48 languages and diverse industrial scenes (digital displays, dot-matrix characters, tire prints, etc.), surpassing Qwen3-VL-235B, GPT-5.5, and Gemini-3.1-Pro with orders of magnitude fewer parameters. PP-OCRv6mediumdet Introduction PP-OCRv6 text detection architecture overview PP-OCRv6mediumdet is the largest model in the PP-OCRv6 detection series developed by the PaddleOCR team. It uses LCNetV4 as the backbone and RepLKFPN as the feature pyramid neck, providing accurate text localization across diverse scenarios including handwritten, printed, rotated, curved, and artistic text in multiple languages. The model contains 15.5M parameters. The key accuracy metrics are as follows: Quick Start Installation This model uses the paddlestatic inference engine by defa
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | PaddlePaddle |
|---|---|
| Type | Language models |
| Variants | 1 |
| Runs with | PaddleOCR |
| Released | 2026-06-10 |
| Popularity | 58k downloads / month |
| Likes | 29 |
| 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 |
|---|---|---|---|---|---|
| PP-OCRv6_medium_det | — | BF16 | — | — | Weights ↗ |
Using it via the API
Once AxForge deploys pp-ocrv6-medium-det for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (pp-ocrv6-medium-det 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":"pp-ocrv6-medium-det","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 ↗