{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/open-weights.document-vision/",
    "json": "https://www.anchorterminal.com/niches/open-weights.document-vision/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/open-weights.document-vision/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/open-weights.document-vision/index.min.md"
  },
  "markdown": "Four or more companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 8 | 14 | 90 | 8 | 4 |\n\n## What counts as done\n\nText or JSON out for every page.\n\nMeasured, for our own tests: word error rate better than Tesseract on the user's sample, and under 60 seconds per page on the stated machine.\n\nHow agents ask for it: OCR these typewritten scans; pull fields from receipts into JSON; read this screenshot; unify thousands of medical record pages\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Gemma 4 12B IT (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))**: Google ships mmproj-gemma-4-12b-it-qat-q4_0.gguf (0.18 GB) beside the Q4_0 GGUF and Ollama's gemma4:12b takes image input; 7 GB fits a 16 GB laptop. No OCR word-error figure for the 12B was found.\n- **Gemma 4 26B A4B IT (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author))**: Google ships gemma-4-26B-it-mmproj.gguf (1.19 GB) beside the Q4_0 GGUF and Ollama's gemma4:26b takes image input; 14.4 GB fits a 24 GB GPU.\n- **Gemma 4 31B IT (Google LLC (the registrant of gemma.ai; the card names Google DeepMind as author))**: Google ships gemma-4-31B-it-mmproj.gguf (1.2 GB) beside the Q4_0 GGUF and Ollama's gemma4:31b takes image input; 17.6 GB fits a 24 GB GPU.\n- **Gemma 4 E4B IT (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))**: Google ships gemma-4-E4B-it-mmproj.gguf (0.99 GB) and Ollama passes images; acc-45 tested Japanese OCR on the family but gives no error rate, and no Tesseract comparison exists.\n- **MiniCPM-o 4.5 (OpenBMB (named as the MiniCPM-o team on the technical report; the GitHub LICENSE is the unfilled Apache template))**: OpenBMB ships the vision GGUF beside every quant, the card lists OCRBench and OmniDocBench results and high-resolution image input, and 5 to 6 GB of files fit a 16 GB laptop.\n- **Muse Glimmer 30B (Meta (the verified Hugging Face organisation is \"Meta Inc.\", the card names Meta Superintelligence Lab, and the licence carries no copyright line))**: Meta ships a 1.4 GB mmproj beside the GGUF and Ollama tags take images, about 22 GB with the build; OmniDocBench 75.8 is Meta's own run and no account tests scans.\n- **Ornith-1.5-9B (Ornith)**: A 0.9 GB mmproj ships beside the GGUFs and Ollama's tag shows vision, but the card gives no document or OCR results.\n- **Qwen3-VL-2B-Instruct (Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder))**: Publisher GGUF ships the mmproj (0.45 GB), llama.cpp b6907 and the Ollama instruct tag pass images, OCR in 32 languages; no account measures WER or seconds per page at this size.\n- **Qwen3-VL-30B-A3B-Instruct (Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder))**: Publisher GGUF ships the mmproj (1.1 GB), llama.cpp b6907 and the Ollama instruct tag pass images, OCR in 32 languages; no account measures WER or seconds per page at this size.\n- **Qwen3-VL-4B-Instruct (Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder))**: Publisher GGUF ships the mmproj (0.45 GB), llama.cpp b6907 and the Ollama instruct tag pass images, OCR in 32 languages; no account measures WER or seconds per page at this size.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Agents-A1-4B (Shanghai Artificial Intelligence Laboratory (the InternAgent team there, per the card's recommended system prompt and the template's default prompt); the GitHub LICENSE leaves the copyright line as the Apache template)**: Vision config present and the publisher's Q4_K_M repository ships Agents-A1-4B-mmproj.gguf (0.67 GB), so llama-server takes images; no OCR result or image test was found and the card documents no vision use.\n- **Apertus v1.5 8B (ETH Zurich and EPFL (the Swiss National AI Institute, named in the Acceptable Use Policy))**: Takes images (image-text-to-text, vision tokenizer shipped) but no mmproj or stock runtime; a third-party Q4_K_M GGUF converts it to the 1.0 apertus architecture, which cannot carry its image path.\n- **Apodex-1.1-mini (Apodex (the site's copyright line reads 2026 Apodex))**: The GGUF repository ships mmproj-apodex1.1-35b-F16.gguf and the card's llama-server line passes --mmproj, so images work; 22.6 GB of files need a 24 GB GPU with little room, and no OCR result exists.\n- **BigBang-v1 (The Endless Frontier (endless-frontier))**: config.json keeps the base's vision tower and bartowski ships an mmproj file, but the card says nothing about images and the publisher ships no GGUF.\n- **Cosmos-Reason2-2B (NVIDIA Corporation)**: Reads images through Qwen3-VL, and a third-party Q4_K_M GGUF ships an mmproj; but NVIDIA states 24 GB minimum GPU memory, ships no quantised build, and trains for physical scenes, not OCR.\n- **Gemma 4 E2B IT (Google LLC (RDAP registrant of gemma.ai as recorded for the first batch's Gemma 4 listings; the card names Google DeepMind as author))**: Google ships gemma-4-E2B-it-mmproj.gguf (0.99 GB) and Ollama's e2b takes images, but no OCR result for E2B was found and acc-45 ran Japanese OCR on the family without reporting E2B as passing.\n- **InternVL3.5-GPT-OSS-20B-A4B-Preview (Shanghai AI Laboratory (OpenGVLab), not named in the repository)**: Reads images and video through InternViT and vLLM loads it; a third-party MXFP4 GGUF (12 GB) with mmproj fits 16 GB under llama.cpp's gpt-oss text architecture, but it is a stale preview trained at 32K with a template that may be wrong, and no OCR result exists.\n- **MiMo-V2.6 Distill Qwen 9B (Xiaomi (the card and report name Xiaomi MiMo; no LICENSE file names a copyright holder))**: The Qwen3.5-9B base keeps a vision tower and Ollama's tag carries a vision badge, but Xiaomi ships no GGUF or mmproj and the card claims nothing about documents.\n- **Nemotron 3 Nano Omni 30B A3B Reasoning (NVIDIA Corporation)**: OCRBenchV2 (EN) 65.8 and a PDF-to-image script on the card, Unsloth GGUFs of 18.5 GB to 24 GB with a 1.6 GB mmproj, Ollama tags take images; scores are NVIDIA's and vLLM needs trust_remote_code.\n- **occamy-1.0 (Accio (Accio-Lab))**: Keeps the base vision tower, a 0.9 GB F16 mmproj ships beside the GGUFs and BF16 passed an image check in vLLM; vision was not retested on the newer quants and no OCR result exists.\n- **Ornith-1.5-35B-A3B (Ornith)**: A 0.9 GB mmproj ships beside the GGUFs and Ollama's tag has a vision badge, but a discussion titled Removed Vision Capabilities is open and the card claims nothing about documents.\n- **Qwen3.5-0.8B (Alibaba Cloud (named in the licence's copyright line))**: Has a vision encoder, but Alibaba ships no GGUF; the mmproj comes from Unsloth's build, and no account reads documents with this size.\n- **Qwen3.5-2B (Alibaba Cloud (named in the licence's copyright line))**: Has a vision encoder, but Alibaba ships no GGUF; the mmproj comes from Unsloth's build, and no account reads documents with this size.\n- **Qwen3.5-4B (Alibaba Cloud (named in the licence's copyright line))**: Vision encoder in config and Ollama's vision badge, but Alibaba ships no GGUF; the mmproj is Unsloth's, and no account measures OCR at this size.\n- **Qwen3.5-9B (Alibaba Cloud (named in the licence's copyright line))**: Vision encoder and Ollama vision badge, but Alibaba ships no GGUF or mmproj; Unsloth's build carries one, and no account measures OCR on the 9B.\n- **Qwen3.6-27B (Alibaba Cloud (named in the licence's copyright line))**: Vision encoder, Ollama vision badge and Unsloth mmproj, 17 to 18 GB with projector on a 24 GB GPU; Alibaba ships no GGUF and no OCR account exists.\n- **Qwen3.6-35B-A3B (Alibaba Cloud (named in the licence's copyright line))**: Vision encoder, Ollama vision badge and Unsloth mmproj, about 23 GB with projector on a 24 GB GPU; Alibaba ships no GGUF and no OCR account exists.\n- **Qwen3.8-27B (Alibaba Cloud (named in the licence's copyright line))**: Vision encoder, Ollama vision badge and Unsloth mmproj; about 18 GB with projector on a 24 GB GPU, but Alibaba ships no GGUF and no OCR account exists.\n- **Qwen3-Omni-30B-A3B-Instruct (Alibaba Cloud (carried from the 20 October 2026 pilot; this model's files name no copyright holder))**: Takes images and llama.cpp lists the ggml-org GGUF with its mmproj (18.6 GB Q4 plus 1.3 GB), fitting a 24 GB GPU; Alibaba ships no GGUF and no OCR account exists.\n- **Qwen3-VL-32B-Instruct (Alibaba Cloud (per the first batch's RDAP check of qwen.ai; this model's files name no copyright holder))**: Publisher GGUF ships the mmproj and 19.8 GB Q4 fits a 24 GB GPU at short context; acc-16 OCRed thousands of medical pages locally but does not name the size.\n- **Qwen3-VL-8B-Instruct (Alibaba Cloud (per the pilot's RDAP check of qwen.ai; this model's files name no copyright holder))**: acc-43 OCRed 600 dpi typewriter scans with the 8B on Ollama, better than Tesseract, but at 5.5 minutes per page on a 16 GB CPU laptop; publisher GGUF ships the mmproj.\n- **Qwopus3.8-27B-Flash-V2 (Jackrong, an individual Hugging Face account)**: The GGUF repository ships mmproj-F32 and the base takes images, 17 GB on a 24 GB GPU; no OCR account and a Hermes-style template the card does not describe.\n- **Swift 1.5 Qwen3.8-27B (UkisAI)**: The GGUF ships a vision projector and 17.4 GB Q4 fits a 24 GB GPU, but the MLX 4-bit build has no image chat, the licence has a revenue cap and no OCR account exists.\n- **ThinkingCap (Qwen3.8 27B) (BottleCap AI (named in the licence's copyright line))**: The GGUF ships an f16 mmproj and the card documents llama-server --mmproj, 17.4 GB fits a 24 GB GPU; licence cap applies and no OCR account exists.\n- **Baidu Unlimited-OCR-2 (Baidu, Inc.)**: Parses scans and rendered PDF pages into text, boxes and HTML tables with 6.7 GB of BF16, but needs trust_remote_code or a repository SGLang wheel, was tested on an A800, and has no publisher GGUF; third-party GGUFs run only in a niche runtime.\n\n- not this job: Carbon-X (Hugging Face (the HuggingFaceBio organisation, named Hugging Face Biology Research on the Hub)): Text only; no vision_config.\n- not this job: Darwin-36B-Opus (VIDRAFT Inc. (named on vidraft.net); the card's citation names FINAL-Bench and VIDRAFT_LAB): Text only; the base's vision encoder is not in the files.\n- not this job: DeepSeek-V3.2 (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)): Text only; no vision_config.\n- not this job: DeepSeek V4.1 Flash (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)): Takes images (vision_config, mmproj in the Unsloth GGUF) but the smallest build is 233 GB, far past a 16 GB laptop or 24 GB GPU.\n- not this job: DeepSeek-V4-Flash-0731 (DeepSeek (the MIT licence names DeepSeek, and DeepSeek's platform terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.)): Text only; no vision_config.\n- not this job: DiffusionGemma 26B A4B IT (Google LLC (RDAP registrant of gemma.ai; the card names Google DeepMind as author)): Takes images, but no released local runtime loads it and Google asks for more than 60 GB of GPU memory.\n- not this job: GLM-4.5-Air (JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai, per the first batch's check on 21 October 2026)): Text only.\n- not this job: GLM-4.7-Flash (JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai)): Text only.\n- not this job: GLM-5.3 (JINGSHENG HENGXING TECHNOLOGY PTE.LTD (operator of Z.ai per its terms of use, and registrant of z.ai). The licence names Z.AI): Text only.\n- not this job: GLM-5.3-Flash (Z.AI Co., Ltd (named in the licence's copyright line)): Takes images and Unsloth ships an mmproj, but the smallest build is 93 GB, far past a 16 GB laptop or 24 GB GPU.\n- not this job: gpt-oss-120b (OpenAI (named as publisher on the card; the openai-api listing's terms name OpenAI OpCo, LLC)): Text only.\n- not this job: gpt-oss-20b (OpenAI (named in USAGE_POLICY and the model card; the LICENSE file's copyright line is the unfilled Apache template)): Text only.\n- not this job: Granite 4.2 3B (International Business Machines Corporation (per IBM's naming guidance, as read for granite-guardian)): Text only.\n- not this job: Hy3 (Tencent (named in the LICENSE file's copyright line)): Text only.\n- not this job: Inkling (Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)): Takes images, but the smallest build is 270 GB.\n- not this job: Inkling-Small (Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)): Takes images and Unsloth ships an mmproj, but 75 GB minimum is far past a 24 GB GPU.\n- not this job: Kimi K3 (Moonshot AI (the licence names Moonshot AI; the Kimi Platform terms name Moonshot AI PTE. LTD.)): Takes images but the smallest build is 466 GB.\n- not this job: Kolibri-1 (Aleph Alpha GmbH): Text only.\n- not this job: Kronos (No company. Yu Shi publishes it from the GitHub account shiyu-coder and the Hugging Face user account NeoQuasar (named ShiYu), with co-authors at Tsinghua University per the paper): No image input.\n- not this job: Laguna M.1 (Poolside, Inc. (named in Poolside's Terms of Use; the LICENSE.md copyright line reads Poolside)): Text only; config.json has no vision tower.\n- not this job: Laguna S 2.1 (Poolside, Inc. (named in Poolside's Terms of Use)): Text only.\n- not this job: Laguna XS 2.1 (Poolside, Inc. (named in Poolside's Terms of Use)): Text only.\n- not this job: LBS-27B (inclusionAI, Ant Group (named in the site footer of inclusion-ai.org); the work is credited to authors from Wuhan University of Technology, CASIA, Zhejiang University and Ant Group): Only BF16 from inclusionAI, about 55 GB of files served with vLLM on four GPUs; no GGUF or mmproj, so nothing fits a 16 GB laptop or 24 GB GPU.\n- not this job: LFM2.5-2.6B (Liquid AI, Inc. (the licensor named in the LFM Open License)): Text only; LFM2.5-VL is a different model.\n- not this job: Ling-3.0-tiny (Ant Intelligence (Hang Zhou) Technology Co., Ltd (named as provider in the training-content summary); inclusionAI, Ant Group in the site footer of inclusion-ai.org): Text only.\n- not this job: MiniCPM5-2B (OpenBMB (named in the GitHub LICENSE's copyright line)): Text only; a discussion asking about vision is unanswered.\n- not this job: MiniMax-M2.5 (MiniMax AI (named in the licences; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)): Text only.\n- not this job: MiniMax-M2.7 (MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)): Text only; MiniMaxM2ForCausalLM has no vision tower.\n- not this job: MiniMax-M3.1-Flash (MiniMax (named in the licence's copyright line; MiniMax's platform terms name Nanonoble Pte. Ltd., Singapore)): Takes images and Unsloth ships mmproj files, but no build fits the 16 GB laptop or 24 GB GPU the use case names.\n- not this job: Mistral Large 4 (Mistral AI (RCS Paris 952 418 325)): Pixtral-style vision encoder and a 3.4 GB mmproj ship, but no build fits the 16 GB laptop or 24 GB GPU the use case names.\n- not this job: Nanbeige4.3-33B (BOSS Zhipin (Kanzhun Limited), unconfirmed): Text only; LlamaForCausalLM with no vision tower.\n- not this job: NVIDIA Nemotron 3.5 Bolt E4B 4GB (NVIDIA Corporation): NVIDIA documents text input only and ships no mmproj beside its GGUF, though the BF16 config keeps Gemma 4's vision_config and Ollama's tag lists Image.\n- not this job: Nemotron 3.5 Lightning 30B A3B (NVIDIA Corporation): Text only; Ollama lists text input and the config has no vision tower.\n- not this job: Nemotron 3 Nano 30B A3B (NVIDIA Corporation): Text only; Ollama lists text input and the config has no vision tower.\n- not this job: Nemotron 3 Nano 4B (NVIDIA Corporation): Text only.\n- not this job: Nemotron 3 Super 120B A12B (NVIDIA Corporation): Text only.\n- not this job: Nemotron 3 Ultra 550B A55B (NVIDIA Corporation): Text only.\n- not this job: Olmo 3 7B Think (The Allen Institute for Artificial Intelligence (Ai2), a 501(c)(3) nonprofit, per its Responsible Use Guidelines): Text only; Olmo3ForCausalLM has no vision tower.\n- not this job: Ornith-1.5-397B (Ornith): An mmproj ships, but the smallest build is 244 GB.\n- not this job: Qwen3-30B-A3B-Instruct-2507 (Alibaba Cloud (named in the licence's copyright line)): Text only; Qwen3MoeForCausalLM has no vision tower.\n- not this job: Qwen3-4B-Instruct-2507 (Alibaba Cloud (named in the licence's copyright line)): Text only; no vision tower in config.json.\n- not this job: Qwen3.5-122B-A10B (Alibaba Cloud (named in the licence's copyright line)): Vision encoder present, but no build fits a 16 GB laptop or 24 GB GPU.\n- not this job: Qwen3.5-397B-A17B (Alibaba Cloud (named in the licence's copyright line)): Vision encoder present but no build fits a 16 GB laptop or 24 GB GPU.\n- not this job: Qwen3.8-Flash-Next (Alibaba Cloud (Singapore) Private Limited, the registrant of qwen.ai. The licence names Qwen as copyright holder): Vision encoder present but no build fits a 16 GB laptop or 24 GB GPU.\n- not this job: Qwen3-Coder-30B-A3B-Instruct (Alibaba Cloud (named in the licence's copyright line)): Text only; no vision tower in config.json.\n- not this job: Qwen3-Coder-Next (Alibaba Cloud (the Qwen team's employer; no LICENSE file names a copyright holder for this model)): Text only; no vision tower in config.json.\n- not this job: Recursive Flint (Recursive Superintelligence, Inc. (the Hugging Face organisation's full name)): Text only; no vision tower in config.json.\n- not this job: Ripple-65B Preview (Ricursive Intelligence, Inc.): Text only; no vision tower in config.json.\n- not this job: SmolLM3-3B (Hugging Face, Inc.): Text only; no vision tower in config.json.\n- not this job: Spark-X2.6-4B (XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM): Text only; no vision tower in config.json.\n- not this job: Swift 1.5 Qwen3.8-Flash-Next (UkisAI): Vision projector shipped, but no build fits a 16 GB laptop or 24 GB GPU.\n\n28 listings in the category were added after this reading and aren't marked yet.\n\n## What stops agents finishing\n\n- GGUF shipped without the mmproj file, so images are ignored\n- Ollama tag loads the Thinking edition instead of Instruct\n- five minutes per page on a 16 GB laptop\n- looping hallucination on repeated glyph patterns\n\n## Around it\n\nBefore: document-extraction.pdf-to-images, file-storage.list. After: document-extraction.table-from-text, spreadsheets.write-rows.\n\n## Where this comes from\n\nWeight 8 of 100 in Open-weight models: 4 of 51 accounts; most vision listings carry no user account\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/open-weights.document-vision.json, or the MCP tool get_use_case with id open-weights.document-vision. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\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": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "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": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Read scans, screenshots and PDF pages locally",
        "url": ""
      }
    ],
    "description": "Read scans, screenshots and PDF pages locally: 8 companies fully do it, 14 with a limit, 90 carry the tag. Every listing in Open-weight models with the reason and a source.",
    "facts": null,
    "h1": "Read scans, screenshots and PDF pages locally",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/open-weights.document-vision/",
    "published": "",
    "section": "agents",
    "title": "Read scans, screenshots and PDF pages locally | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/open-weights.document-vision/"
  },
  "tokens": {
    "markdown": 5050,
    "slim": 1030
  },
  "version": 1
}
