Model reference · open weights
HunyuanOCR is an open-weight language model from tencent, 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
HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better 🤗 HF Model | 💻 GitHub Repo | 📄 Paper 📦 Model layout. This repository hosts HunyuanOCR-1.5 checkpoint at the root (target base weights). The DFlash speculative-decoding draft lives under dflash/, and the previous HunyuanOCR-1.0 is archived under v1.0/ (load it with subfolder="v1.0", or download the v1.0/ directory directly). 📖 Introduction HunyuanOCR-1.5 is a lightweight, end-to-end OCR-specialized vision-language model. It targets a broad range of text-centric visual tasks and unifies document parsing, text spotting, information extraction, text-image translation within a single end-to-end VLM. Building upon the validated lightweight architecture of HunyuanOCR-1.0, HunyuanOCR-1.5 does not redesign the model backbone. Instead, it performs a systematic upgrade around two goals — making the model faster and better: - ⚡ Faster — DFlash inference acceleration. End-to-end OCR is often accompanied by long autoregressive decoding, which becomes the major bottleneck for dense documents, tables, formulas, and other long structured outputs. HunyuanOCR-1.5 adapts a speculative-decoding framework based on DFlash: a lightweight block-diffusion draft model drafts multiple candidate tokens in parallel, which are then verified by the target model in a single pass. This significantly reduces the decoding latency of long structured outputs while preserving the output distribution of the target model. - 💻 PC-side deployment via llama.cpp. Beyond server-grade vLLM, HunyuanOCR-1.5 also supports CPU / consumer-GPU / laptop deployment through llama.cpp with a GGUF-converted checkpoint and an OpenAI-compatible llama-server. A DFlash-adapted llama.cpp fork is provided as well, so the same speculative-decoding acceleration is available on PC. - 🧠 Better — Agentic Data Flow + upgraded training recipe. On the data side, we propose Agentic Data Flow, an agent-driven data-construction system that translates model weaknesses into executable data requirements. Agents deeply participate in material search, tool-based verification, sample cleaning, and data-pipeline development, and iterate in a closed loop with algorithm engineers. In
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | tencent |
|---|---|
| Type | Language models |
| Parameters (lead) | 1.1B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2025-11-18 |
| Popularity | 685k downloads / month |
| Likes | 812 |
| Licence | Commercial licence needed |
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 |
|---|---|---|---|---|---|
| HunyuanOCR | 1.1B | BF16 | ~2.6 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys hunyuanocr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (hunyuanocr 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":"hunyuanocr","messages":[{"role":"user","content":"Hello"}]}'
Licence
The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗