Chandra OCR 2 vs Baidu Unlimited-OCR-2

Chandra OCR 2 33

Model card 8, Intended use and the languages (over 90) are on the card. Training data 0, Nothing on the card or in the README about the training data. Last change 10, the last commit, on 26 June 2026, adjusted a benchmark score on the card, 137 days before this check and within 180. Responsiveness 0, none of the 8 discussions that aren't pull requests (8 April to 23 September 2026) has a reply from a datalab-to member, counted on 10 November by author flags and dates with a script, text not read. Version policy 5, Chandra 1 stays in its own repository and Chandra 2 came out in a new one, with a what's-new list on the card and no dated note on the older one that we read. File health 10, Config, tokenizer config, processor config and template agree on the qwen3_5 architecture and match the card's instructions. 8 + 0 + 10 + 0 + 5 + 10 = 33.

Baidu Unlimited-OCR-2 50

The card covers intended use and the new attention, and misses limitations, parameters, context length, languages and a cut-off (5). Training data is described by mix and labelling with no datasets named and no cut-off (5). The card changed on 2 November 2026 and the SGLang wheel on 29 October (20). Baidu's uploader replied in 1 of the 5 Hub discussions, a few (5). The first model stays in its own repository without a note pointing here (5), and the files agree with the card (10).

Chandra OCR 2 65

Memory 30, the only build from Datalab is the BF16 safetensors file, 10.59 GB, and 10.59 GB × 1.2 = 12.7 GB, within 16 GB. No runtime library has a build. Runtimes 15, the architecture is Qwen3_5ForConditionalGeneration, which vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.2 run from the safetensors file, three at 5 each. Builds 0, Datalab publishes the BF16 weights only for this model. Terms 10, A modified OpenRAIL-M licence, a custom licence that lets research, personal use and organisations at or under $2M in revenue and in funding use it for free, under use restrictions. 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 + 10 + 10 + 0 = 65.

Baidu Unlimited-OCR-2 55

Memory earns the full 30, since the only build is 6.69 GB of BF16 weights that need about 8 GB with the fifth added. Runtimes score 0. Released vLLM 0.33.0, SGLang 0.5.23 and Transformers 5.22.1 know the first Unlimited-OCR but not the sparse attention this one adds, Baidu's own routes are remote code in Transformers and a customised SGLang wheel, llama.cpp b12111 has nothing for it, so Ollama has nothing either, and LM Studio couldn't be checked. Builds score 0, as Baidu publishes no quantised build (16 exist, all by others). Terms get 15 for MIT with nothing added. Download gets 10 for an ungated repository, and hosted too 0, with no inference provider mapped and the card's Baidu Cloud line unconfirmed.

Chandra OCR 2 70

Chat template 20, chat_template.jinja in the repository (7,622 characters), Qwen 3.5's template, with a copy in tokenizer_config.json. 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 run without reasoning. Context 0, Datalab states no context length for it. 20 + 25 + 10 + 15 + 0 + 0 = 70.

Baidu Unlimited-OCR-2 75

Read for a document parser, the tool-calling, trained tool calling and structured-output lines stand for what it takes and returns. Baidu documents the page images, the prompt, the request settings and the block output, and ships a converter for the server's output (25). It was trained to read many pages in one request (20). The block format with classes, boxes and HTML tables, and its conversion to Markdown, are documented with how to get them (15). The prompt is built in code, with no Jinja template in the repository (10). Reasoning control scores 0, and the context 5, trained at up to 64K tokens.