{ "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": "Nemotron 3.5 Parse scores 69 (B) on agent readiness against HunyuanOCR 1.5's 56.6 (C), and leads in 2 of 4 scored categories. HunyuanOCR 1.5 leads on agent interface.", "b": { "slug": "nemotron-3-5-parse", "name": "Nemotron 3.5 Parse", "vendor": "NVIDIA", "vendorUrl": "https://developer.nvidia.com/nemotron", "kind": "weights", "category": "document-extraction", "summary": "Nemotron 3.5 Parse is NVIDIA's open-weight document parser, 0.63B parameters, that turns a page image into text with layout classes, bounding boxes and reading order, and renders Markdown, HTML tables and JSON, under OpenMDW-1.1.", "url": "https://www.anchorterminal.com/tools/nemotron-3-5-parse", "markdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-parse.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-parse.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-parse.json", "dns": "nemotron-3-5-parse.grade.anchorterminal.com", "repo": "https://huggingface.co/nvidia/Nemotron-3.5-Parse", "license": "OpenMDW-1.1", "transports": [], "packages": [ { "registry": "huggingface", "name": "nvidia/Nemotron-3.5-Parse" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-22). The card's line about running hf auth login 'if repository access requires authentication' doesn't apply today.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under OpenMDW-1.1 (the Linux Foundation's permissive model licence), with the tokenizer under MIT. NVIDIA sells no per-call access to these weights in this listing. Running them costs the hardware, a 2.52 GB F32 safetensors file loaded in BF16 on one NVIDIA GPU; NVIDIA's reference hardware is one H100. No inference provider serves it on Hugging Face (checked 2026-10-22).", "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 2026-10-22).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-01" }, "docsUrl": "https://huggingface.co/nvidia/Nemotron-3.5-Parse/blob/main/docs/serving.md", "capabilities": [ "docs.parse", "docs.ocr", "docs.tables", "model.open-weights" ], "tags": [ "open-weights", "model", "document-parsing", "ocr", "layout", "tables", "charts", "bounding-boxes", "multilingual", "vision", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-28", "graded": true, "anchor": { "graded": true, "score": 69, "grade": "B", "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": 4, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 83, "interface": 70, "reach": 60, "risk": 60, "upkeep": 59 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-01" }, "negative": 0, "verdict": "A small document-parsing cousin that turns page images into Markdown, HTML tables and JSON with layout classes and boxes, under a permissive licence. It needs a GPU with a few GB, runs in vLLM 0.33, and NVIDIA's API serves it. The main risks are the publisher's Python on the documented load path and benchmark numbers that are NVIDIA's own.", "bestFor": "Agents and pipelines with an NVIDIA GPU that need fast local page parsing into Markdown, tables and boxed blocks for retrieval or extraction", "strengths": [ "Tiny, 0.63B parameters in one 2.52 GB safetensors file, about 3 GB in memory", "Layout classes, bounding boxes and reading order on every block, with helpers for Markdown, HTML tables, JSON and CSV", "OpenMDW-1.1 with nothing added, ungated, files hashed in NVIDIA's own organisation", "An OpenAI-compatible server through vLLM, a Dockerfile, a CLI with single, double and triple pass, and a runnable ParseBench reproduction bundle", "Earlier Parse releases kept in their own repositories, with a dated pointer to this one", "NVIDIA's API catalogue serves it as a free endpoint, and vLLM v0.33.0 registers its architecture natively" ], "weaknesses": [ "Loading runs the publisher's Python with trust_remote_code, in Transformers and in vLLM through NVIDIA's plugin", "Only vLLM, from v0.33.0, runs it from its own code, the card still pins an earlier vLLM, and NVIDIA publishes no quantised build", "One page per request with a 16,384-token context, so documents are parsed page by page", "Its ParseBench result is NVIDIA's own run; LlamaIndex's leaderboard row copies the card's numbers", "No safety results, training data without named datasets or a cut-off, and nobody has asked anything in its repository yet" ], "agentNotes": [ "Quickest local run, Python 3.12 with `pip install \"transformers==5.14.1\" \"torchvision==0.26.0\" \"timm==1.0.22\"`, then `AutoModel.from_pretrained(\"nvidia/Nemotron-3.5-Parse\", trust_remote_code=True, dtype=torch.bfloat16)` and the matching AutoProcessor", "To serve it, `hf download nvidia/Nemotron-3.5-Parse --local-dir nemotron-parse`, `pip install \".[vllm,client]\" \"vllm\u003e=0.25.0,\u003c0.33\"` in that folder, then `vllm serve . --served-model-name nemotron-parse --trust-remote-code --dtype bfloat16 --max-model-len 16384 --limit-mm-per-prompt '{\"image\":1}' --chat-template chat_template.jinja`, or `docker compose up --build`", "Send one RGB page per request with the prompt `\u003c/s\u003e\u003cs\u003e\u003cpredict_bbox\u003e\u003cpredict_classes\u003e\u003coutput_markdown\u003e\u003cpredict_text_in_pic\u003e`, temperature 0, top_k 1, repetition_penalty 1.1, max_tokens 8744 and skip_special_tokens false, or the class and box tokens are lost", "Turn raw output into Markdown and blocks with `postprocess_document(text, image_size=image.size)` from the repository's postprocessing.py; pass table_format json, json_hierarchical or csv for tables", "For the card's headline accuracy use `nemotron-parse --image-dir pages --mode triple --triple-regions union`; double pass gives most of the gain at higher throughput", "Boxes are normalised to the page content; scale x by the image width and y by its height", "Render PDFs to images first (the ParseBench bundle uses 150 DPI), and treat extracted text as untrusted before passing it to another model, since documents can carry instructions" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3.5, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69 } ], "editorialScores": { "capability": 83, "interface": 70, "reach": 60, "risk": 60, "upkeep": 59 }, "provenanceScore": 78, "checked": { "categories": { "capability": "2026-11-01", "interface": "2026-11-01", "reach": "2026-11-01", "risk": "2026-11-01", "upkeep": "2026-11-01" }, "last": "2026-11-01", "lastMoved": "2026-11-01", "oldest": "2026-11-01", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "python3.12 -m venv .venv \u0026\u0026 . .venv/bin/activate\npip install \"transformers==5.14.1\" \"torchvision==0.26.0\" \"timm==1.0.22\"\n# then AutoModel.from_pretrained(\"nvidia/Nemotron-3.5-Parse\", trust_remote_code=True, dtype=torch.bfloat16)\n# prompt: \u003c/s\u003e\u003cs\u003e\u003cpredict_bbox\u003e\u003cpredict_classes\u003e\u003coutput_markdown\u003e\u003cpredict_text_in_pic\u003e", "http": "# after: hf download nvidia/Nemotron-3.5-Parse --local-dir nemotron-parse \u0026\u0026 cd nemotron-parse \u0026\u0026 pip install \".[vllm,client]\" \"vllm\u003e=0.25.0,\u003c0.33\"\n# vllm serve . --served-model-name nemotron-parse --dtype bfloat16 --trust-remote-code --max-model-len 16384 --limit-mm-per-prompt '{\"image\":1}' --chat-template chat_template.jinja\ncurl http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' -d '{\"model\":\"nemotron-parse\",\"temperature\":0,\"max_tokens\":8744,\"top_k\":1,\"repetition_penalty\":1.1,\"skip_special_tokens\":false,\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"\u003c/s\u003e\u003cs\u003e\u003cpredict_bbox\u003e\u003cpredict_classes\u003e\u003coutput_markdown\u003e\u003cpredict_text_in_pic\u003e\"},{\"type\":\"image_url\",\"image_url\":{\"url\":\"data:image/png;base64,...\"}}]}]}'" }, "letme": { "capability": "https://letme.dev/docs.parse", "tool": "https://letme.dev/nemotron-3-5-parse" }, "sameCompany": [ "nemotron-3-5-super-vl", "nvidia-nemo-retriever", "nemo-guardrails", "nemotron-3-5-asr-streaming-0-6b", "nemotron-3-5-transcribe-30b-a4b", "parakeet-tdt-0-6b-v3", "parakeet-unified-en-0-6b", "cosmos-reason2-2b", "nemotron-3-5-bolt-e4b-4gb", "nemotron-3-nano-30b-a3b", "nemotron-3-nano-4b", "nemotron-3-nano-omni-30b-a3b-reasoning", "nemotron-3-super-120b-a12b", "nemotron-3-ultra-550b-a55b", "nemotron-3-5-lightning-30b-a3b" ], "weights": { "trainedBy": "NVIDIA", "builtOn": "nvidia/C-RADIOv4-SO400M (the vision encoder the card names; NVIDIA's own, under the NVIDIA Open Model License)", "params": "0.63B", "context": 16384, "goodFor": "Turning scanned or rendered document pages into Markdown, HTML tables and JSON blocks with layout classes, boxes and reading order, fast on one GPU, for retrieval, extraction and data-curation pipelines.", "runtimes": [ "vLLM" ], "builds": [ { "name": "Nemotron-3.5-Parse (safetensors)", "url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse/blob/main/model.safetensors", "who": "publisher", "precision": "fp32", "sizeGB": 2.52, "memoryGB": 8, "format": "safetensors", "runsOn": [ "Transformers (remote code)", "vLLM (NVIDIA's plugin)" ], "note": "Stored in F32 and loaded in BF16 per the card. The only build from NVIDIA; 2,523,266,640 bytes, SHA-256 81dd7609c589f369..." } ], "run": "hf download nvidia/Nemotron-3.5-Parse --local-dir nemotron-parse \u0026\u0026 cd nemotron-parse \u0026\u0026 pip install \".[vllm,client]\" \"vllm\u003e=0.25.0,\u003c0.33\" \u0026\u0026 vllm serve . --served-model-name nemotron-parse --dtype bfloat16 --trust-remote-code --max-model-len 16384 --no-enable-prefix-caching --limit-mm-per-prompt '{\"image\":1}' --chat-template chat_template.jinja", "runBuild": "Nemotron-3.5-Parse (safetensors)", "checked": "2026-11-01", "minMemoryGB": 8 }, "family": { "lab": "NVIDIA (Nemotron)", "family": "Nemotron 3", "url": "https://www.anchorterminal.com/open-weights/#nvidia", "others": [ { "name": "Nemotron 3 Nano 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "params": "30B total, 3B active (31.6B per the safetensors index)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-30b-a3b" }, { "name": "Nemotron 3 Nano 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3 Super 120B-A12B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", "params": "120B total, 12B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-super-120b-a12b" }, { "name": "Nemotron 3 Super 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3 Nano 4B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16", "params": "4B", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-4b" }, { "name": "Nemotron 3 Nano Omni 30B-A3B Reasoning", "url": "https://huggingface.co/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-nano-omni-30b-a3b-reasoning" }, { "name": "Nemotron 3 Ultra 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "params": "550B total, 55B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-ultra-550b-a55b" }, { "name": "Nemotron 3 Ultra 550B-A55B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Ultra 550B-A55B GenRM", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-GenRM", "params": "550B total, 55B active" }, { "name": "Nemotron 3.5 Lightning 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "params": "30B total, 3B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-lightning-30b-a3b" }, { "name": "Nemotron 3.5 Lightning 30B-A3B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-Base-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron 3.5 Super VL 120B-A12B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16", "params": "120B total, 12B active", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-super-vl" }, { "name": "Nemotron 3.5 Super VL 120B-A12B Base", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16", "params": "120B total, 12B active" }, { "name": "Nemotron 3.5 Bolt 74B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16", "params": "74B total, 9B active" }, { "name": "Nemotron 3.5 Bolt E4B 4GB", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB", "params": "8B total, 4B effective", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-bolt-e4b-4gb" }, { "name": "Nemotron Labs 3 Elastic 30B-A3B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Elastic-30B-A3B-BF16", "params": "30B total, 3B active" }, { "name": "Nemotron Labs 3 Puzzle 75B-A9B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16", "params": "75B total, 9B active" }, { "name": "Nemotron 3 Labs Ultra Math SFT", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-SFT", "params": "550B total, 55B active" }, { "name": "Nemotron 3 Labs Ultra Math RL", "url": "https://huggingface.co/nvidia/Nemotron-3-Labs-Ultra-Math-RL", "params": "550B total, 55B active" }, { "name": "Nemotron Labs 3 Competitive Coding 550B-A55B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-3-Competitive-Coding-550B-A55B-NVFP4", "params": "550B total, 55B active" }, { "name": "nemotron-3.5-asr-streaming-0.6b", "url": "https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b", "params": "0.6B (638M per the safetensors count)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-asr-streaming-0-6b" }, { "name": "Nemotron 3.5 Transcribe 30B-A4B", "url": "https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B", "params": "30B total, about 4.3B active (33,697,781,029 by the Hub's safetensors count)", "listing": "https://www.anchorterminal.com/tools/nemotron-3-5-transcribe-30b-a4b" } ], "olderCount": 47 }, "area": "web-data", "provenance": { "legalEntity": "NVIDIA Corporation", "domain": "nvidia.com", "domainRegistered": "1993-04-20", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/nvidia/Nemotron-3.5-Parse/commits/main", "securityTxt": "unknown", "checked": "2026-10-22", "notes": [ "The card says the model was developed by NVIDIA as part of Nemotron, and the files sit in NVIDIA's verified nvidia organisation on Hugging Face, which developer.nvidia.com links to. The domain registration date is carried from the RDAP check made for nemotron-3-super-120b-a12b on 21 October 2026.", "Nothing is hosted in this listing, so the OpenMDW-1.1 licence stands in for terms of service and no privacy policy is scored. The privacy subcard links NVIDIA's privacy policy.", "The changelog is the repository's commit history, four commits from 18 to 21 October 2026 (the release, refreshed regression references, a fix to malformed block parsing in the reference pipelines, and a merged pull request widening the vLLM range), all by NVIDIA organisation members. The repository was created on 3 September 2026 and its earlier history isn't public.", "www.nvidia.com/.well-known/security.txt was not requested; earlier NVIDIA listings record a 403. The card links NVIDIA's vulnerability submission page." ], "score": 78 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nemotron-3-5-parse.json", "live": { "slug": "nemotron-3-5-parse", "securityTxt": { "url": "https://nvidia.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-10T16:08:00.271598775Z" }, "domain": { "domain": "nvidia.com", "registered": "1993-04-20", "source": "https://rdap.verisign.com/com/v1/domain/nvidia.com", "checkedAt": "2026-11-08T15:03:11.895084282Z" }, "pages": [ { "url": "https://huggingface.co/nvidia/Nemotron-3.5-Parse/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-11-10T16:23:30.724078931Z", "changedAt": "2026-11-10T16:23:30.724078931Z", "fingerprint": "655ab448397f" } ], "updatedAt": "2026-11-10T16:23:30.724078931Z" } }, "edges": [ { "by": 15, "category": "risk", "leads": "nemotron-3-5-parse", "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 gets 15, safetensors only but loaded with trust_remote_code in both documented runtimes. Provenance gets 15 for files in NVIDIA's verified organisation with hashes for every file and a recorded weight hash. Licence risk keeps 15, since OpenMDW-1.1 has none of the deductions. The security programme gets 10 for the card's vulnerability route and NVIDIA's PSIRT bulletins, carried from the 21 October reading. Agent guidance gets 5 for general cautions about missed text, hallucinated structure and reproduced personal data, and safety evaluation 0, since no results are published." }, "scores": { "a": 45, "b": 60 } }, { "by": 11, "category": "upkeep", "leads": "nemotron-3-5-parse", "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": "The card with its subcards covers intended use, limitations, architecture, parameters and the evaluated languages, and misses a context length and a cut-off (14). Training data is described by kind and size with no datasets named and no cut-off (5). The card changed on 28 October 2026 (20). Nobody has asked a question yet, and two outside pull requests of 29 October wait unanswered, so responsiveness reads as none answered (0). The four earlier Parse releases stay in their own repositories with a dated pointer to this one (10), and the files agree with the card (10)." }, "scores": { "a": 48, "b": 59 } }, { "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": "Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. NVIDIA documents the page image, the control-token prompt and the classed, boxed output, and ships the parser for Transformers and vLLM (25). It was trained for one page per request (10). Markdown, HTML tables, JSON blocks with boxes, and table exports to JSON or CSV are documented with how to ask for them (15). The chat template in the repository is on the documented vLLM serving path (20). Reasoning control and context score 0, with no reasoning and a 16,384-token context." }, "scores": { "a": 80, "b": 70 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Tencent (Hy team)", "b": "NVIDIA", "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": "OpenMDW-1.1", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-08-28", "b": "2026-10-28", "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" }, { "a": "none", "b": "3.5/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Nemotron 3.5 Parse scores 69 (B) on agent readiness against HunyuanOCR 1.5's 56.6 (C), and leads in 2 of 4 scored categories. HunyuanOCR 1.5 leads on agent interface.", "question": "Which is better for AI agents, HunyuanOCR 1.5 or Nemotron 3.5 Parse?" } ], "goodFor": [ { "aheadOn": [ "Agent interface, 80 against 70" ], "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": [ "Risk, 60 against 45", "Documentation and upkeep, 59 against 48" ], "also": null, "goodFor": "Agents and pipelines with an NVIDIA GPU that need fast local page parsing into Markdown, tables and boxed blocks for retrieval or extraction", "slug": "nemotron-3-5-parse", "watchFor": "Loading runs the publisher's Python with trust_remote_code, in Transformers and in vLLM through NVIDIA's plugin" } ], "history": { "hunyuanocr": null, "nemotron-3-5-parse": [ { "causes": [ "product" ], "date": "2026-11-01", "delta": 2.5, "from": 66.5, "fromGrade": "B", "to": 69, "toGrade": "B" } ] }, "job": { "capability": "docs.ocr", "name": "OCR" }, "others": [ { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-surya-ocr-2-5.json", "title": "Nemotron 3.5 Parse vs Surya OCR 2.5", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-surya-ocr-2-5" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-xiaomi-ocr-0.json", "title": "Nemotron 3.5 Parse vs Xiaomi-OCR-0", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-xiaomi-ocr-0" }, { "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-nemotron-3-5-parse.json", "title": "Chandra OCR 2 vs Nemotron 3.5 Parse", "url": "https://www.anchorterminal.com/compare/chandra-ocr-2-vs-nemotron-3-5-parse" }, { "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-nemotron-3-5-parse.json", "title": "DeepSeek-OCR 2 vs Nemotron 3.5 Parse", "url": "https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-nemotron-3-5-parse" }, { "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-nanonets-ocr2-3b.json", "title": "HunyuanOCR 1.5 vs Nanonets-OCR2-3B", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b" }, { "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-nemotron-3-5-parse.json", "title": "LightOnOCR-3-4B vs Nemotron 3.5 Parse", "url": "https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nemotron-3-5-parse" }, { "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" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 0, "edge": "", "hunyuanocr": 60, "key": "reach", "name": "Reach", "nemotron-3-5-parse": 60, "weight": 25 }, { "by": 15, "edge": "nemotron-3-5-parse", "hunyuanocr": 45, "key": "risk", "name": "Risk", "nemotron-3-5-parse": 60, "weight": 20 }, { "by": 10, "edge": "hunyuanocr", "hunyuanocr": 80, "key": "interface", "name": "Agent interface", "nemotron-3-5-parse": 70, "weight": 10 }, { "by": 11, "edge": "nemotron-3-5-parse", "hunyuanocr": 48, "key": "upkeep", "name": "Documentation and upkeep", "nemotron-3-5-parse": 59, "weight": 10 } ], "summary": "Nemotron 3.5 Parse scores 69 (B) on agent readiness against HunyuanOCR 1.5's 56.6 (C), and leads in 2 of 4 scored categories. HunyuanOCR 1.5 leads on agent interface. 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.", "nemotron-3-5-parse": "A small document-parsing cousin that turns page images into Markdown, HTML tables and JSON with layout classes and boxes, under a permissive licence. It needs a GPU with a few GB, runs in vLLM 0.33, and NVIDIA's API serves it. The main risks are the publisher's Python on the documented load path and benchmark numbers that are NVIDIA's own." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse", "json": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.min.md" }, "markdown": "Nemotron 3.5 Parse scores 69 (B) on agent readiness against HunyuanOCR 1.5's 56.6 (C), and leads in 2 of 4 scored categories. HunyuanOCR 1.5 leads on agent interface. 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- Nemotron 3.5 Parse: grade B, 69/100, rank #10 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/nemotron-3-5-parse.md · JSON https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-parse.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- Agent interface, 80 against 70\n\nWatch for: The licence doesn't apply in the EU, the UK or South Korea\n\n### Nemotron 3.5 Parse (B)\n\nGood for: Agents and pipelines with an NVIDIA GPU that need fast local page parsing into Markdown, tables and boxed blocks for retrieval or extraction\n\nAhead on:\n- Risk, 60 against 45\n- Documentation and upkeep, 59 against 48\n\nWatch for: Loading runs the publisher's Python with trust_remote_code, in Transformers and in vLLM through NVIDIA's plugin\n\n\n## Why the edge\n\n### Risk: Nemotron 3.5 Parse +15\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- Nemotron 3.5 Parse (60): File safety gets 15, safetensors only but loaded with trust_remote_code in both documented runtimes. Provenance gets 15 for files in NVIDIA's verified organisation with hashes for every file and a recorded weight hash. Licence risk keeps 15, since OpenMDW-1.1 has none of the deductions. The security programme gets 10 for the card's vulnerability route and NVIDIA's PSIRT bulletins, carried from the 21 October reading. Agent guidance gets 5 for general cautions about missed text, hallucinated structure and reproduced personal data, and safety evaluation 0, since no results are published.\n\n### Documentation and upkeep: Nemotron 3.5 Parse +11\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- Nemotron 3.5 Parse (59): The card with its subcards covers intended use, limitations, architecture, parameters and the evaluated languages, and misses a context length and a cut-off (14). Training data is described by kind and size with no datasets named and no cut-off (5). The card changed on 28 October 2026 (20). Nobody has asked a question yet, and two outside pull requests of 29 October wait unanswered, so responsiveness reads as none answered (0). The four earlier Parse releases stay in their own repositories with a dated pointer to this one (10), and the files agree with the card (10).\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- Nemotron 3.5 Parse (70): Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. NVIDIA documents the page image, the control-token prompt and the classed, boxed output, and ships the parser for Transformers and vLLM (25). It was trained for one page per request (10). Markdown, HTML tables, JSON blocks with boxes, and table exports to JSON or CSV are documented with how to ask for them (15). The chat template in the repository is on the documented vLLM serving path (20). Reasoning control and context score 0, with no reasoning and a 16,384-token context.\n\n## Score by category\n\n| Category | Weight | HunyuanOCR 1.5 | Nemotron 3.5 Parse | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 60 | 60 | even |\n| Risk | 20% (20 this run) | 45 | 60 | Nemotron 3.5 Parse +15 |\n| Agent interface | 10% (10 this run) | 80 | 70 | HunyuanOCR 1.5 +10 |\n| Documentation and upkeep | 10% (10 this run) | 48 | 59 | Nemotron 3.5 Parse +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **56.6 · C** | **69 · B** | |\n\n## Facts side by side\n\n| Fact | HunyuanOCR 1.5 | Nemotron 3.5 Parse |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Tencent (Hy team) | NVIDIA |\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) | OpenMDW-1.1 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-08-28 | 2026-10-28 |\n| Terms last updated | not read yet | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | none | 3.5/5 (4) |\n\n## How the scores have moved\n\n### HunyuanOCR 1.5\n\nNo score change since it was listed.\n\n### Nemotron 3.5 Parse\n\n- +2.5 on 1 November 2026: product\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**Nemotron 3.5 Parse.** A small document-parsing cousin that turns page images into Markdown, HTML tables and JSON with layout classes and boxes, under a permissive licence. It needs a GPU with a few GB, runs in vLLM 0.33, and NVIDIA's API serves it. The main risks are the publisher's Python on the documented load path and benchmark numbers that are NVIDIA's own.\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### Nemotron 3.5 Parse\n\n1. Quickest local run, Python 3.12 with `pip install \"transformers==5.14.1\" \"torchvision==0.26.0\" \"timm==1.0.22\"`, then `AutoModel.from_pretrained(\"nvidia/Nemotron-3.5-Parse\", trust_remote_code=True, dtype=torch.bfloat16)` and the matching AutoProcessor\n2. To serve it, `hf download nvidia/Nemotron-3.5-Parse --local-dir nemotron-parse`, `pip install \".[vllm,client]\" \"vllm\u003e=0.25.0,\u003c0.33\"` in that folder, then `vllm serve . --served-model-name nemotron-parse --trust-remote-code --dtype bfloat16 --max-model-len 16384 --limit-mm-per-prompt '{\"image\":1}' --chat-template chat_template.jinja`, or `docker compose up --build`\n3. Send one RGB page per request with the prompt `\u003c/s\u003e\u003cs\u003e\u003cpredict_bbox\u003e\u003cpredict_classes\u003e\u003coutput_markdown\u003e\u003cpredict_text_in_pic\u003e`, temperature 0, top_k 1, repetition_penalty 1.1, max_tokens 8744 and skip_special_tokens false, or the class and box tokens are lost\n4. Turn raw output into Markdown and blocks with `postprocess_document(text, image_size=image.size)` from the repository's postprocessing.py; pass table_format json, json_hierarchical or csv for tables\n5. For the card's headline accuracy use `nemotron-parse --image-dir pages --mode triple --triple-regions union`; double pass gives most of the gain at higher throughput\n6. Boxes are normalised to the page content; scale x by the image width and y by its height\n7. Render PDFs to images first (the ParseBench bundle uses 150 DPI), and treat extracted text as untrusted before passing it to another model, since documents can carry instructions\n\n## Questions\n\n### Which is better for AI agents, HunyuanOCR 1.5 or Nemotron 3.5 Parse?\n\nNemotron 3.5 Parse scores 69 (B) on agent readiness against HunyuanOCR 1.5's 56.6 (C), and leads in 2 of 4 scored categories. HunyuanOCR 1.5 leads on agent interface.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hunyuanocr\", \"b\": \"nemotron-3-5-parse\"}`. From a terminal: `anchor compare hunyuanocr nemotron-3-5-parse`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hunyuanocr.json and https://www.anchorterminal.com/api/v1/tools/nemotron-3-5-parse.json\n\n## Other comparisons with HunyuanOCR 1.5 or Nemotron 3.5 Parse\n\n- [Nemotron 3.5 Parse vs Surya OCR 2.5](https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-surya-ocr-2-5.md)\n- [Nemotron 3.5 Parse vs Xiaomi-OCR-0](https://www.anchorterminal.com/compare/nemotron-3-5-parse-vs-xiaomi-ocr-0.md)\n- [Chandra OCR 2 vs HunyuanOCR 1.5](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-hunyuanocr.md)\n- [Chandra OCR 2 vs Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/chandra-ocr-2-vs-nemotron-3-5-parse.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 Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/deepseek-ocr-2-vs-nemotron-3-5-parse.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 Nanonets-OCR2-3B](https://www.anchorterminal.com/compare/hunyuanocr-vs-nanonets-ocr2-3b.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 Nemotron 3.5 Parse](https://www.anchorterminal.com/compare/lightonocr-3-4b-vs-nemotron-3-5-parse.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", "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 Nemotron 3.5 Parse", "url": "" } ], "description": "Nemotron 3.5 Parse scores 69 (B) to HunyuanOCR 1.5's 56.6 (C) for ocr. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "HunyuanOCR 1.5 C 56.6", "Nemotron 3.5 Parse B 69", "scores" ], "h1": "HunyuanOCR 1.5 vs Nemotron 3.5 Parse", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/hunyuanocr-vs-nemotron-3-5-parse", "published": "2026-10-01", "section": "tools", "title": "HunyuanOCR 1.5 vs Nemotron 3.5 Parse for AI agents (2026)", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/hunyuanocr-vs-nemotron-3-5-parse" }, "tokens": { "markdown": 3300, "slim": 730 }, "version": 1 }