{ "data": { "a": { "slug": "hunyuanocr", "name": "HunyuanOCR 1.5", "vendor": "Tencent (Hy team)", "vendorUrl": "https://aistudio.tencent.com", "kind": "weights", "category": "document-extraction", "summary": "HunyuanOCR 1.5 is Tencent's open-weight OCR model of 1.1B parameters for document parsing, text spotting, information extraction and translating text in images, with a 128K context, under a licence that doesn't apply in the EU, the UK or South Korea.", "url": "https://www.anchorterminal.com/tools/hunyuanocr", "markdownUrl": "https://www.anchorterminal.com/tools/hunyuanocr.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hunyuanocr.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hunyuanocr.json", "dns": "hunyuanocr.grade.anchorterminal.com", "repo": "https://huggingface.co/tencent/HunyuanOCR", "license": "Tencent Hunyuan Community License (not licensed in the EU, the UK or South Korea)", "transports": [], "packages": [ { "registry": "huggingface", "name": "tencent/HunyuanOCR" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download. The Tencent Hunyuan Community License allows commercial use under Tencent's acceptable use policy, except for anyone with more than 100 million monthly active users, and it doesn't apply in the European Union, the United Kingdom or South Korea, where it grants no rights. Running it yourself costs little hardware, 2.24 GB in BF16 (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://github.com/Tencent-Hunyuan/HunyuanOCR", "capabilities": [ "docs.ocr", "docs.parse", "docs.extract", "docs.tables", "model.open-weights" ], "tags": [ "open-weights", "model", "ocr", "document-parsing", "text-spotting", "information-extraction", "translation", "vision", "custom-licence", "territory-limit", "safetensors", "self-hosted" ], "lastRelease": "2026-08-28", "graded": true, "anchor": { "graded": true, "score": 56.6, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 19, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 80, "reach": 60, "risk": 45, "upkeep": 48 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "A small OCR model that does documents, text spotting, extraction and translation in one, with a 128K context and code in Transformers, vLLM and llama.cpp. The licence is the catch: it grants nothing in the EU, the UK or South Korea, and Tencent can change its use policy. No quantised build, safety results or data sources.", "bestFor": "Teams outside the EU, the UK and South Korea that want one small model for OCR, extraction and image translation", "strengths": [ "Four OCR jobs in one 1.1B model, with several images in a request", "A 128K context, trained for it per the card", "Released Transformers, vLLM and llama.cpp have the architecture", "Fits any machine: 2.24 GB in BF16", "The card documents prompts, settings and three ways to run it" ], "weaknesses": [ "The licence doesn't apply in the EU, the UK or South Korea", "Tencent can update the acceptable use policy, and a 100 million user threshold applies", "No GGUF or other quantised build from Tencent", "Version 1.5 replaced 1.0 in the same repository", "A few of the questions on the repository answered", "No limitations, safety results or data sources on the card" ], "agentNotes": [ "Check where you and your users are first. The licence grants no rights in the European Union, the United Kingdom or South Korea", "Download with `--exclude \"v1.0/*\"` so the old version isn't fetched", "Serve it with vLLM 0.25.1 or later at `--max-model-len 131072`, or use Tencent's scripts on GitHub for its sampling and post-processing", "Use temperature 0, top_p 1 and repetition_penalty 1.08", "The default document prompt is in Chinese and is on the card. Other tasks take their own instruction as the prompt", "For llama.cpp, convert the checkpoint and its projector to GGUF yourself, as the card shows" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 56.6 } ], "editorialScores": { "interface": 80, "reach": 60, "risk": 45, "upkeep": 48 }, "provenanceScore": 68, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install \"vllm\u003e=0.25.1\"\nhf download tencent/HunyuanOCR --local-dir ./HunyuanOCR --exclude \"v1.0/*\"\nvllm serve ./HunyuanOCR --served-model-name tencent/HunyuanOCR --max-model-len 131072\n# Tencent's own scripts, with its sampling and post-processing, are in github.com/Tencent-Hunyuan/HunyuanOCR (inference/vLLM/serve.sh)", "http": "# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1. Send one image with a task prompt,\n# temperature 0, top_p 1 and repetition_penalty 1.08, per the card" }, "letme": { "capability": "https://letme.dev/docs.ocr", "tool": "https://letme.dev/hunyuanocr" }, "sameCompany": [ "hy-memory", "tencentdb-agent-memory", "hy-memory-30b-a3b", "hy3", "wevisone-vl-2b", "wevisone-vl-4b" ], "weights": { "trainedBy": "Tencent Hunyuan", "params": "1.1B", "context": 131072, "goodFor": "Small, fast OCR for documents, text in photos, field extraction and translating text in images, where the licence applies. It doesn't in the EU, the UK or South Korea.", "runtimes": [ "llama.cpp", "vLLM", "Transformers" ], "builds": [ { "name": "HunyuanOCR 1.5 (BF16 safetensors)", "url": "https://huggingface.co/tencent/HunyuanOCR/blob/main/model.safetensors", "who": "publisher", "precision": "bf16", "sizeGB": 2.24, "memoryGB": 8, "format": "safetensors", "runsOn": [ "vLLM", "Transformers" ], "note": "The root of the repository. Leave out the v1.0 folder when downloading, as the card says" } ], "run": "vllm serve tencent/HunyuanOCR --max-model-len 131072", "runBuild": "HunyuanOCR 1.5 (BF16 safetensors)", "checked": "2026-11-10", "minMemoryGB": 8 }, "family": { "lab": "Tencent (Hunyuan / Hy)", "family": "HunyuanOCR", "url": "https://www.anchorterminal.com/open-weights/#tencent", "olderCount": 22 }, "area": "web-data", "provenance": { "legalEntity": "Tencent (named in the LICENSE file's copyright line)", "domain": "tencent.com", "domainRegistered": "1998-09-14", "endpointOnVendorDomain": null, "terms": "https://huggingface.co/tencent/HunyuanOCR/raw/main/LICENSE", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/tencent/HunyuanOCR/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The licence names Tencent. The domain's registration date is carried from our other Tencent listings.", "Nothing is hosted under this listing, so the model licence stands in for terms of service and no privacy policy is scored.", "The changelog is the commit history, 50 commits or more since 18 November 2025, the last two on 26 and 28 August 2026 changing config.json.", "Tencent's Security Response Center takes reports company-wide, per the Hy3 listing; nothing on the card links it." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hunyuanocr.json" }, "answer": "HunyuanOCR 1.5 scores 56.6 (C) on agent readiness against Nanonets-OCR2-3B's 48.1 (D), and leads in every scored category.", "b": { "slug": "nanonets-ocr2-3b", "name": "Nanonets-OCR2-3B", "vendor": "Nanonets", "vendorUrl": "https://nanonets.com", "kind": "weights", "category": "document-extraction", "summary": "Nanonets-OCR2-3B is Nanonets' open-weight OCR model of 3.75B parameters, a fine-tune of Qwen2.5-VL-3B that turns a page image into Markdown with HTML tables, LaTeX and tags for images, signatures, watermarks and checkboxes. It states no licence.", "url": "https://www.anchorterminal.com/tools/nanonets-ocr2-3b", "markdownUrl": "https://www.anchorterminal.com/tools/nanonets-ocr2-3b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nanonets-ocr2-3b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nanonets-ocr2-3b.json", "dns": "nanonets-ocr2-3b.grade.anchorterminal.com", "repo": "https://huggingface.co/nanonets/Nanonets-OCR2-3B", "license": "None stated (the base model, Qwen2.5-VL-3B-Instruct, is under the Qwen Research licence)", "transports": [], "packages": [ { "registry": "huggingface", "name": "nanonets/Nanonets-OCR2-3B" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository is not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download, but nothing says what you may do with it. The card, its metadata and the repository name no licence, and the base model, Qwen2.5-VL-3B-Instruct, is under the Qwen Research licence. Ask Nanonets before any commercial use. Running it yourself costs the hardware, 7.51 GB in BF16 (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://github.com/NanoNets/Nanonets-OCR2", "capabilities": [ "docs.ocr", "docs.parse", "docs.tables", "model.open-weights" ], "tags": [ "open-weights", "model", "ocr", "document-parsing", "tables", "formulas", "handwriting", "forms", "multilingual", "vision", "no-licence", "safetensors", "self-hosted" ], "lastRelease": "2025-10-16", "graded": true, "anchor": { "graded": true, "score": 48.1, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 23, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 70, "reach": 55, "risk": 40, "upkeep": 25 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "A well-used 3.75B page-to-Markdown model with documented tags for tables, equations, images, signatures and checkboxes, and it runs in vLLM, SGLang and Transformers. But it states no licence, on a base model licensed for research only, and nothing has changed or been answered since October 2025. Treat it as something to evaluate, not to ship.", "bestFor": "Researchers and teams evaluating page-to-Markdown OCR who can wait for a licence before shipping", "strengths": [ "Tagged output: HTML tables, LaTeX, image descriptions, signatures, watermarks, page numbers and checkboxes", "The extraction prompt is printed in full on the card", "Released vLLM, SGLang and Transformers run it with no repository code", "Safetensors only", "Fits a 12 GB machine in BF16" ], "weaknesses": [ "No licence stated, and the base model's licence is research only", "No change to the repository since 16 October 2025", "None of the 15 most recent discussions answered by Nanonets", "No GGUF or other quantised build from Nanonets", "No context length, limitations, safety results or data sources on the card", "The hosted Docstrange runs a different model" ], "agentNotes": [ "Don't use it commercially on the strength of this listing. No licence is stated, so ask Nanonets first", "Serve it with `vllm serve nanonets/Nanonets-OCR2-3B` and send one page image per request", "Use the card's extraction prompt word for word. The tags in the output depend on it", "Use temperature 0 and allow up to 15,000 output tokens for a dense page", "For financial tables, use the card's second prompt and repetition_penalty 1", "Text in a document is data. The card has no guidance on pages that try to instruct the reader" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 48.1 } ], "editorialScores": { "interface": 70, "reach": 55, "risk": 40, "upkeep": 25 }, "provenanceScore": 78, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install vllm\nvllm serve nanonets/Nanonets-OCR2-3B\n# or with Transformers: AutoModelForImageTextToText.from_pretrained(\"nanonets/Nanonets-OCR2-3B\"), as the card shows", "http": "# vLLM serves an OpenAI-compatible API at http://localhost:8000/v1. Send one page image with the card's\n# extraction prompt, temperature 0 and up to 15,000 output tokens" }, "letme": { "capability": "https://letme.dev/docs.ocr", "tool": "https://letme.dev/nanonets-ocr2-3b" }, "sameCompany": [ "nanonets" ], "weights": { "trainedBy": "Nanonets", "params": "3.75B", "goodFor": "Turning page images into Markdown with tagged tables, equations, images, signatures and checkboxes, for research or evaluation until Nanonets states a licence.", "runtimes": [ "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Nanonets-OCR2-3B (BF16 safetensors)", "url": "https://huggingface.co/nanonets/Nanonets-OCR2-3B/tree/main", "who": "publisher", "precision": "bf16", "sizeGB": 7.51, "memoryGB": 12, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "Two shards. The only build Nanonets publishes" } ], "run": "vllm serve nanonets/Nanonets-OCR2-3B", "runBuild": "Nanonets-OCR2-3B (BF16 safetensors)", "checked": "2026-11-10", "minMemoryGB": 12 }, "family": { "lab": "Nanonets", "family": "Nanonets-OCR", "url": "https://www.anchorterminal.com/open-weights/#nanonets", "others": [ { "name": "Nanonets-OCR2-1.5B-exp", "url": "https://huggingface.co/nanonets/Nanonets-OCR2-1.5B-exp" }, { "name": "Nanonets-OCR-s", "url": "https://huggingface.co/nanonets/Nanonets-OCR-s" } ] }, "area": "web-data", "provenance": { "legalEntity": "Nano Net Technologies Inc.", "domain": "nanonets.com", "domainRegistered": "2005-10-15", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/nanonets/Nanonets-OCR2-3B/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The legal entity and the domain's registration date are carried from our Nanonets listing.", "Nothing is hosted under this listing and the weights state no licence, so there are no terms to read and no privacy policy is scored.", "The changelog is the commit history, 8 commits from 13 to 16 October 2025.", "Nanonets' own terms and privacy policy cover its hosted service, not these weights." ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nanonets-ocr2-3b.json" }, "edges": [ { "by": 23, "category": "upkeep", "leads": "hunyuanocr", "name": "Documentation and upkeep", "reasons": { "a": "Model card 8, Intended use, the architecture by reference to 1.0's unchanged backbone, and the context (128K) are on the card. Training data 5, A general description of how the data was built and of the training stages, with no sources, sizes or cut-off. Last change 15, the last commit, on 28 August 2026, changed config.json, 74 days before this check and within 90. Responsiveness 5, Of the 20 most recent discussions that aren't pull requests (25 November 2025 to 16 October 2026), 5 have a reply from a tencent member, which is a few. Version policy 5, Version 1.5 replaced 1.0 at the root of the same repository. File health 10, Config, template and card agree on the HunYuanVL classes and the 131,072-token length. 8 + 5 + 15 + 5 + 5 + 10 = 48.", "b": "Model card 5, Intended use and the languages are on the card. Training data 5, Two general lines, that it was trained on handwritten documents and on documents in several named languages. Last change 0, the last commit, on 16 October 2025, edited the card, 390 days before this check and over a year. Responsiveness 0, none of the 15 most recent discussions that aren't pull requests (13 October 2025 to 21 October 2026) has a reply from a nanonets member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, the earlier Nanonets-OCR-s stays in its own repository and OCR2 came out in new ones, with no dated note on the older one that we read. File health 10, Config, template and card agree on the Qwen2.5-VL classes. 5 + 5 + 0 + 0 + 5 + 10 = 25." }, "scores": { "a": 48, "b": 25 } }, { "by": 10, "category": "interface", "leads": "hunyuanocr", "name": "Agent interface", "reasons": { "a": "Chat template 20, chat_template.jinja in the repository (930 characters). Tool-calling format 25, Read for a document parser as what it takes and returns. Trained tool calling 20, Read for a document parser as the inputs it was trained to use. Structured output 5, Read for a document parser as typed outputs. Reasoning control 0, A document parser with no reasoning. Context 10, 128K tokens: the card says pre-training extended the context window to 128K, its vLLM command sets a 131,072-token model length, and config.json gives the language model 131,072 positions. 20 + 25 + 20 + 5 + 0 + 10 = 80.", "b": "Chat template 20, chat_template.jinja in the repository (1,017 characters), Qwen's ChatML format with image placeholders. Tool-calling format 25, Read for a document parser as what it takes and returns. Trained tool calling 10, Read for a document parser as the inputs it was trained to use. Structured output 15, Read for a document parser as typed outputs. Reasoning control 0, A document parser with no reasoning. Context 0, Nanonets states no context length for it. 20 + 25 + 10 + 15 + 0 + 0 = 70." }, "scores": { "a": 80, "b": 70 } }, { "by": 5, "category": "reach", "leads": "hunyuanocr", "name": "Reach", "reasons": { "a": "Memory 30, the only build from Tencent is the BF16 safetensors file at the root, 2.24 GB, and 2.24 GB × 1.2 = 2.7 GB, within 16 GB. ggml-org's GGUF (Q8_0 0.58 GB with a 0.73 GB projector) dates from 21 May 2026 and wasn't matched to version 1.5. Runtimes 15, Released Transformers 5.22.2 has the hunyuan_vl model, vLLM 0.33.0 registers HunYuanVLForConditionalGeneration, and llama.cpp b12242 has the architecture, which the card says the community build runs after conversion. Builds 0, Tencent publishes the BF16 weights only and tells users to convert to GGUF themselves. Terms 5, A custom licence that allows free commercial use under a use policy and below 100 million monthly active users, but not for anyone: it doesn't apply in the European Union, the United Kingdom or South Korea. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and the card names no Tencent API that serves it. 30 + 15 + 0 + 5 + 10 + 0 = 60.", "b": "Memory 30, the only build from Nanonets is the BF16 safetensors files, 7.51 GB, and 7.51 GB × 1.2 = 9.0 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen2_5_VLForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors files, three at 5 each. Builds 0, Nanonets publishes the BF16 weights only. Terms 0, no licence. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 30 + 15 + 0 + 0 + 10 + 0 = 55." }, "scores": { "a": 60, "b": 55 } }, { "by": 5, "category": "risk", "leads": "hunyuanocr", "name": "Risk", "reasons": { "a": "File safety 25, safetensors only, no .bin, .pt or .pth files, and no Python at the root. Provenance 15, the files sit in the tencent organisation, which Tencent's GitHub repository for the model links to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or use section, and nothing on text in an image that tries to instruct the reader. Licence risk 0, 15 less 5 for limits beyond the law (an acceptable use policy and three territories where the licence doesn't apply), 5 for terms the licensor can change (Tencent may update the policy from time to time) and 5 for the 100 million monthly active user threshold. Security programme 5, Tencent's Security Response Center takes vulnerability reports company-wide, as the Hy3 listing records (5). 25 + 15 + 0 + 0 + 0 + 5 = 45.", "b": "File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the nanonets organisation, which the card ties to nanonets.com and Nanonets' GitHub cookbook repository is written for by the model's name (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, Nothing on text in a document that tries to instruct the reader, on what the model refuses or on safeguards to add. Licence risk 0, With no licence there is nothing to hold Nanonets to. Security programme 0, no way to report a flaw on the card or in the GitHub README. Our Nanonets listing found no security.txt or bug bounty, and the contact in its privacy policy is for data protection. 25 + 15 + 0 + 0 + 0 + 0 = 40." }, "scores": { "a": 45, "b": 40 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Tencent (Hy team)", "b": "Nanonets", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Tencent Hunyuan Community License (not licensed in the EU, the UK or South Korea)", "b": "None stated (the base model, Qwen2.5-VL-3B-Instruct, is under the Qwen Research licence)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-08-28", "b": "2025-10-16", "name": "Last release" }, { "a": "not read yet", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" } ], "faq": [ { "answer": "HunyuanOCR 1.5 scores 56.6 (C) on agent readiness against Nanonets-OCR2-3B's 48.1 (D), and leads in every scored category.", "question": "Which is better for AI agents, HunyuanOCR 1.5 or Nanonets-OCR2-3B?" } ], "goodFor": [ { "aheadOn": [ "Reach, 60 against 55", "Risk, 45 against 40", "Agent interface, 80 against 70", "Documentation and upkeep, 48 against 25" ], "also": null, "goodFor": "Teams outside the EU, the UK and South Korea that want one small model for OCR, extraction and image translation", "slug": "hunyuanocr", "watchFor": "The licence doesn't apply in the EU, the UK or South Korea" }, { "aheadOn": null, "also": null, "goodFor": "Researchers and teams evaluating page-to-Markdown OCR who can wait for a licence before shipping", "slug": "nanonets-ocr2-3b", "watchFor": "No licence stated, and the base model's licence is research only" } ], "history": null, "job": { "capability": "docs.ocr", "name": "OCR" }, "others": [ { "json": "https://www.anchorterminal.com/compare/chandra-ocr-2-vs-hunyuanocr.json", "title": "Chandra OCR 2 vs HunyuanOCR 1.5", "url": "https://www.anchorterminal.com/compare/chandra-ocr-2-vs-hunyuanocr" }, { "json": "https://www.anchorterminal.com/compare/chandra-ocr-2-vs-nanonets-ocr2-3b.json", "title": "Chandra OCR 2 vs Nanonets-OCR2-3B", "url": "https://www.anchorterminal.com/compare/chandra-ocr-2-vs-nanonets-ocr2-3b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr.json", "title": "DeepSeek-OCR 2 vs HunyuanOCR 1.5", "url": "https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr" }, { "json": "https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-nanonets-ocr2-3b.json", "title": "DeepSeek-OCR 2 vs Nanonets-OCR2-3B", "url": "https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-nanonets-ocr2-3b" }, { "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-lightonocr-3-4b.json", "title": "HunyuanOCR 1.5 vs LightOnOCR-3-4B", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-lightonocr-3-4b" }, { "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.json", "title": "HunyuanOCR 1.5 vs Nemotron 3.5 Parse", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse" }, { "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-surya-ocr-2-5.json", "title": "HunyuanOCR 1.5 vs Surya OCR 2.5", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-surya-ocr-2-5" }, { "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-unlimited-ocr-2.json", "title": "HunyuanOCR 1.5 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-xiaomi-ocr-0.json", "title": "HunyuanOCR 1.5 vs Xiaomi-OCR-0", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-xiaomi-ocr-0" }, { "json": "https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nanonets-ocr2-3b.json", "title": "LightOnOCR-3-4B vs Nanonets-OCR2-3B", "url": "https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nanonets-ocr2-3b" }, { "json": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-nemotron-3-5-parse.json", "title": "Nanonets-OCR2-3B vs Nemotron 3.5 Parse", "url": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-nemotron-3-5-parse" }, { "json": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-surya-ocr-2-5.json", "title": "Nanonets-OCR2-3B vs Surya OCR 2.5", "url": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-surya-ocr-2-5" }, { "json": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-unlimited-ocr-2.json", "title": "Nanonets-OCR2-3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-xiaomi-ocr-0.json", "title": "Nanonets-OCR2-3B vs Xiaomi-OCR-0", "url": "https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-xiaomi-ocr-0" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 5, "edge": "hunyuanocr", "hunyuanocr": 60, "key": "reach", "name": "Reach", "nanonets-ocr2-3b": 55, "weight": 25 }, { "by": 5, "edge": "hunyuanocr", "hunyuanocr": 45, "key": "risk", "name": "Risk", "nanonets-ocr2-3b": 40, "weight": 20 }, { "by": 10, "edge": "hunyuanocr", "hunyuanocr": 80, "key": "interface", "name": "Agent interface", "nanonets-ocr2-3b": 70, "weight": 10 }, { "by": 23, "edge": "hunyuanocr", "hunyuanocr": 48, "key": "upkeep", "name": "Documentation and upkeep", "nanonets-ocr2-3b": 25, "weight": 10 } ], "summary": "HunyuanOCR 1.5 scores 56.6 (C) on agent readiness against Nanonets-OCR2-3B's 48.1 (D), and leads in every scored category. Both do ocr.", "tasks": null, "tutorials": [], "verdicts": { "hunyuanocr": "A small OCR model that does documents, text spotting, extraction and translation in one, with a 128K context and code in Transformers, vLLM and llama.cpp. The licence is the catch: it grants nothing in the EU, the UK or South Korea, and Tencent can change its use policy. No quantised build, safety results or data sources.", "nanonets-ocr2-3b": "A well-used 3.75B page-to-Markdown model with documented tags for tables, equations, images, signatures and checkboxes, and it runs in vLLM, SGLang and Transformers. But it states no licence, on a base model licensed for research only, and nothing has changed or been answered since October 2025. Treat it as something to evaluate, not to ship." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b", "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.min.md" }, "markdown": "HunyuanOCR 1.5 scores 56.6 (C) on agent readiness against Nanonets-OCR2-3B's 48.1 (D), and leads in every scored category. Both do ocr.\n\n- HunyuanOCR 1.5: grade C, 56.6/100, rank #114 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/hunyuanocr.md · JSON https://www.anchorterminal.com/api/v1/tools/hunyuanocr.json\n- Nanonets-OCR2-3B: grade D, 48.1/100, rank #153 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/nanonets-ocr2-3b.md · JSON https://www.anchorterminal.com/api/v1/tools/nanonets-ocr2-3b.json\n- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md\n- All 215 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md\n\n## Which one, for what\n\n### HunyuanOCR 1.5 (C)\n\nGood for: Teams outside the EU, the UK and South Korea that want one small model for OCR, extraction and image translation\n\nAhead on:\n- Reach, 60 against 55\n- Risk, 45 against 40\n- Agent interface, 80 against 70\n- Documentation and upkeep, 48 against 25\n\nWatch for: The licence doesn't apply in the EU, the UK or South Korea\n\n### Nanonets-OCR2-3B (D)\n\nGood for: Researchers and teams evaluating page-to-Markdown OCR who can wait for a licence before shipping\n\nWatch for: No licence stated, and the base model's licence is research only\n\n\n## Why the edge\n\n### Documentation and upkeep: HunyuanOCR 1.5 +23\n\n- HunyuanOCR 1.5 (48): Model card 8, Intended use, the architecture by reference to 1.0's unchanged backbone, and the context (128K) are on the card. Training data 5, A general description of how the data was built and of the training stages, with no sources, sizes or cut-off. Last change 15, the last commit, on 28 August 2026, changed config.json, 74 days before this check and within 90. Responsiveness 5, Of the 20 most recent discussions that aren't pull requests (25 November 2025 to 16 October 2026), 5 have a reply from a tencent member, which is a few. Version policy 5, Version 1.5 replaced 1.0 at the root of the same repository. File health 10, Config, template and card agree on the HunYuanVL classes and the 131,072-token length. 8 + 5 + 15 + 5 + 5 + 10 = 48.\n- Nanonets-OCR2-3B (25): Model card 5, Intended use and the languages are on the card. Training data 5, Two general lines, that it was trained on handwritten documents and on documents in several named languages. Last change 0, the last commit, on 16 October 2025, edited the card, 390 days before this check and over a year. Responsiveness 0, none of the 15 most recent discussions that aren't pull requests (13 October 2025 to 21 October 2026) has a reply from a nanonets member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, the earlier Nanonets-OCR-s stays in its own repository and OCR2 came out in new ones, with no dated note on the older one that we read. File health 10, Config, template and card agree on the Qwen2.5-VL classes. 5 + 5 + 0 + 0 + 5 + 10 = 25.\n\n### Agent interface: HunyuanOCR 1.5 +10\n\n- HunyuanOCR 1.5 (80): Chat template 20, chat_template.jinja in the repository (930 characters). Tool-calling format 25, Read for a document parser as what it takes and returns. Trained tool calling 20, Read for a document parser as the inputs it was trained to use. Structured output 5, Read for a document parser as typed outputs. Reasoning control 0, A document parser with no reasoning. Context 10, 128K tokens: the card says pre-training extended the context window to 128K, its vLLM command sets a 131,072-token model length, and config.json gives the language model 131,072 positions. 20 + 25 + 20 + 5 + 0 + 10 = 80.\n- Nanonets-OCR2-3B (70): Chat template 20, chat_template.jinja in the repository (1,017 characters), Qwen's ChatML format with image placeholders. Tool-calling format 25, Read for a document parser as what it takes and returns. Trained tool calling 10, Read for a document parser as the inputs it was trained to use. Structured output 15, Read for a document parser as typed outputs. Reasoning control 0, A document parser with no reasoning. Context 0, Nanonets states no context length for it. 20 + 25 + 10 + 15 + 0 + 0 = 70.\n\n### Reach: HunyuanOCR 1.5 +5\n\n- HunyuanOCR 1.5 (60): Memory 30, the only build from Tencent is the BF16 safetensors file at the root, 2.24 GB, and 2.24 GB × 1.2 = 2.7 GB, within 16 GB. ggml-org's GGUF (Q8_0 0.58 GB with a 0.73 GB projector) dates from 21 May 2026 and wasn't matched to version 1.5. Runtimes 15, Released Transformers 5.22.2 has the hunyuan_vl model, vLLM 0.33.0 registers HunYuanVLForConditionalGeneration, and llama.cpp b12242 has the architecture, which the card says the community build runs after conversion. Builds 0, Tencent publishes the BF16 weights only and tells users to convert to GGUF themselves. Terms 5, A custom licence that allows free commercial use under a use policy and below 100 million monthly active users, but not for anyone: it doesn't apply in the European Union, the United Kingdom or South Korea. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it, and the card names no Tencent API that serves it. 30 + 15 + 0 + 5 + 10 + 0 = 60.\n- Nanonets-OCR2-3B (55): Memory 30, the only build from Nanonets is the BF16 safetensors files, 7.51 GB, and 7.51 GB × 1.2 = 9.0 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen2_5_VLForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors files, three at 5 each. Builds 0, Nanonets publishes the BF16 weights only. Terms 0, no licence. Download 10, the Hub API reports gated false on 10 November 2026, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps no inference provider to it. 30 + 15 + 0 + 0 + 10 + 0 = 55.\n\n### Risk: HunyuanOCR 1.5 +5\n\n- HunyuanOCR 1.5 (45): File safety 25, safetensors only, no .bin, .pt or .pth files, and no Python at the root. Provenance 15, the files sit in the tencent organisation, which Tencent's GitHub repository for the model links to (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, the card has no limitations or use section, and nothing on text in an image that tries to instruct the reader. Licence risk 0, 15 less 5 for limits beyond the law (an acceptable use policy and three territories where the licence doesn't apply), 5 for terms the licensor can change (Tencent may update the policy from time to time) and 5 for the 100 million monthly active user threshold. Security programme 5, Tencent's Security Response Center takes vulnerability reports company-wide, as the Hy3 listing records (5). 25 + 15 + 0 + 0 + 0 + 5 = 45.\n- Nanonets-OCR2-3B (40): File safety 25, safetensors only, no .bin, .pt or .pth files and no Python in the repository. Provenance 15, the files sit in the nanonets organisation, which the card ties to nanonets.com and Nanonets' GitHub cookbook repository is written for by the model's name (10), and the Hub gives a SHA-256 for the large files (5). Safety evaluation 0, no safety results on the card. Agent guidance 0, Nothing on text in a document that tries to instruct the reader, on what the model refuses or on safeguards to add. Licence risk 0, With no licence there is nothing to hold Nanonets to. Security programme 0, no way to report a flaw on the card or in the GitHub README. Our Nanonets listing found no security.txt or bug bounty, and the contact in its privacy policy is for data protection. 25 + 15 + 0 + 0 + 0 + 0 = 40.\n\n## Score by category\n\n| Category | Weight | HunyuanOCR 1.5 | Nanonets-OCR2-3B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 60 | 55 | HunyuanOCR 1.5 +5 |\n| Risk | 20% (20 this run) | 45 | 40 | HunyuanOCR 1.5 +5 |\n| Agent interface | 10% (10 this run) | 80 | 70 | HunyuanOCR 1.5 +10 |\n| Documentation and upkeep | 10% (10 this run) | 48 | 25 | HunyuanOCR 1.5 +23 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **56.6 · C** | **48.1 · D** | |\n\n## Facts side by side\n\n| Fact | HunyuanOCR 1.5 | Nanonets-OCR2-3B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Tencent (Hy team) | Nanonets |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Tencent Hunyuan Community License (not licensed in the EU, the UK or South Korea) | None stated (the base model, Qwen2.5-VL-3B-Instruct, is under the Qwen Research licence) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-08-28 | 2025-10-16 |\n| Terms last updated | not read yet | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n\n## Verdicts\n\n**HunyuanOCR 1.5.** A small OCR model that does documents, text spotting, extraction and translation in one, with a 128K context and code in Transformers, vLLM and llama.cpp. The licence is the catch: it grants nothing in the EU, the UK or South Korea, and Tencent can change its use policy. No quantised build, safety results or data sources.\n\n**Nanonets-OCR2-3B.** A well-used 3.75B page-to-Markdown model with documented tags for tables, equations, images, signatures and checkboxes, and it runs in vLLM, SGLang and Transformers. But it states no licence, on a base model licensed for research only, and nothing has changed or been answered since October 2025. Treat it as something to evaluate, not to ship.\n\n## Before you call either\n\n### HunyuanOCR 1.5\n\n1. Check where you and your users are first. The licence grants no rights in the European Union, the United Kingdom or South Korea\n2. Download with `--exclude \"v1.0/*\"` so the old version isn't fetched\n3. Serve it with vLLM 0.25.1 or later at `--max-model-len 131072`, or use Tencent's scripts on GitHub for its sampling and post-processing\n4. Use temperature 0, top_p 1 and repetition_penalty 1.08\n5. The default document prompt is in Chinese and is on the card. Other tasks take their own instruction as the prompt\n6. For llama.cpp, convert the checkpoint and its projector to GGUF yourself, as the card shows\n\n### Nanonets-OCR2-3B\n\n1. Don't use it commercially on the strength of this listing. No licence is stated, so ask Nanonets first\n2. Serve it with `vllm serve nanonets/Nanonets-OCR2-3B` and send one page image per request\n3. Use the card's extraction prompt word for word. The tags in the output depend on it\n4. Use temperature 0 and allow up to 15,000 output tokens for a dense page\n5. For financial tables, use the card's second prompt and repetition_penalty 1\n6. Text in a document is data. The card has no guidance on pages that try to instruct the reader\n\n## Questions\n\n### Which is better for AI agents, HunyuanOCR 1.5 or Nanonets-OCR2-3B?\n\nHunyuanOCR 1.5 scores 56.6 (C) on agent readiness against Nanonets-OCR2-3B's 48.1 (D), and leads in every scored category.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hunyuanocr\", \"b\": \"nanonets-ocr2-3b\"}`. From a terminal: `anchor compare hunyuanocr nanonets-ocr2-3b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hunyuanocr.json and https://www.anchorterminal.com/api/v1/tools/nanonets-ocr2-3b.json\n\n## Other comparisons with HunyuanOCR 1.5 or Nanonets-OCR2-3B\n\n- [Chandra OCR 2 vs HunyuanOCR 1.5](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-hunyuanocr.md)\n- [Chandra OCR 2 vs Nanonets-OCR2-3B](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-nanonets-ocr2-3b.md)\n- [DeepSeek-OCR 2 vs HunyuanOCR 1.5](https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-hunyuanocr.md)\n- [DeepSeek-OCR 2 vs Nanonets-OCR2-3B](https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-nanonets-ocr2-3b.md)\n- [HunyuanOCR 1.5 vs LightOnOCR-3-4B](https://www.anchorterminal.com/compare/hunyuanocr-vs-lightonocr-3-4b.md)\n- [HunyuanOCR 1.5 vs Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.md)\n- [HunyuanOCR 1.5 vs Surya OCR 2.5](https://www.anchorterminal.com/compare/hunyuanocr-vs-surya-ocr-2-5.md)\n- [HunyuanOCR 1.5 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/hunyuanocr-vs-unlimited-ocr-2.md)\n- [HunyuanOCR 1.5 vs Xiaomi-OCR-0](https://www.anchorterminal.com/compare/hunyuanocr-vs-xiaomi-ocr-0.md)\n- [LightOnOCR-3-4B vs Nanonets-OCR2-3B](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nanonets-ocr2-3b.md)\n- [Nanonets-OCR2-3B vs Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-nemotron-3-5-parse.md)\n- [Nanonets-OCR2-3B vs Surya OCR 2.5](https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-surya-ocr-2-5.md)\n- [Nanonets-OCR2-3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-unlimited-ocr-2.md)\n- [Nanonets-OCR2-3B vs Xiaomi-OCR-0](https://www.anchorterminal.com/compare/nanonets-ocr2-3b-vs-xiaomi-ocr-0.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "HunyuanOCR 1.5 vs Nanonets-OCR2-3B", "url": "" } ], "description": "HunyuanOCR 1.5 scores 56.6 (C) to Nanonets-OCR2-3B's 48.1 (D) for ocr. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "HunyuanOCR 1.5 C 56.6", "Nanonets-OCR2-3B D 48.1", "scores" ], "h1": "HunyuanOCR 1.5 vs Nanonets-OCR2-3B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/hunyuanocr-vs-nanonets-ocr2-3b", "published": "2026-10-01", "section": "tools", "title": "HunyuanOCR 1.5 vs Nanonets-OCR2-3B for AI agents (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b" }, "tokens": { "markdown": 3550, "slim": 730 }, "version": 1 }