Not licensed for UK or EU use, so British developers should look elsewhere for document OCR.
Kenning's take
What it does
HunyuanOCR is a lightweight vision-language model from Tencent that handles document parsing, finding text in images, pulling out fields and translating text in pictures in one model. Version 1.5, released in July 2026, made it faster and added local PC deployment through llama.cpp. Weights and training code are on Hugging Face and GitHub under Tencent's community licence.
- Document parsing
- Text spotting in photos
- Information extraction
- Text-in-image translation
- Runs locally via llama.cpp (v1.5)
Who it suits. Developers building document scanning, data entry or translation features.
Key facts
- Category
- AI models
- Made by
- Tencent
- Based in
- China
- Released
- 25 November 2025
- How to get it
- open weights on Hugging Face and code on GitHub; Tencent's licence states it does not apply in the UK, EU or South Korea
- Works on
- open-weights
- In the UK
- No
- Free plan
- yes, open weights (outside the UK, EU and South Korea)
FAQ
When was HunyuanOCR released?
Tencent's licence gives 25 November 2025; version 1.5 followed on 7 July 2026.
Can HunyuanOCR run on a PC?
Version 1.5 added PC deployment through llama.cpp.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.
Cisco Antares
Cisco's small open-weight models that find where known security vulnerabilities sit in a codebase, running locally.