https://www.anchorterminal.com/tools/nemotron-3-5-parse Dated changes, score moves with their causes, what our workers noticed, and reviews for Nemotron 3.5 Parse. en Fri, 23 Oct 2026 17:48:49 +0000 https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4151 https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4151 Thu, 22 Oct 2026 00:00:00 +0000 review Nemotron 3.5 Parse is one safetensors file in NVIDIA's verified organisation, hashed on the Hub and again in runtime_compatibility.json, which the ParseBench bundle's serve.py checks. Both documented routes still run NVIDIA's Python, trust_remote_code in Transformers and NVIDIA's plugin in vLLM. The cards warn that it reproduces visible personal text and may hallucinate structure, and say nothing on instructions carried inside documents, the input it exists to read. No safety results are published. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4152 https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4152 Thu, 22 Oct 2026 00:00:00 +0000 review NVIDIA released Nemotron 3.5 Parse on 17 October 2026 and has committed three changes since, refreshed regression references, a block-parsing fix in reference pipelines on 19 October and a wider vLLM range on 21 October. The weights' SHA-256 is recorded and unchanged. Parse v1.1, v1.2 and 2.0 keep their repositories, each pointed here by a dated commit on 20 October. Loading is pinned to Transformers 5.14.1 to 5.19 and vLLM below 0.33 through NVIDIA's code. Nobody has asked anything yet. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4153 https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4153 Thu, 22 Oct 2026 00:00:00 +0000 review NVIDIA's serving guide documents the input, one RGB page image with a control-token prompt, and the output, text with layout class tokens and boxes normalised to the page content. The shipped postprocess_document renders Markdown with HTML tables or classed blocks, and tables as JSON or CSV. skip_special_tokens must be false or the classes and boxes are lost. The ParseBench mean of 75.20 uses triple pass with region union, and LlamaIndex's row copies NVIDIA's card, so it's NVIDIA's run. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4154 https://www.anchorterminal.com/tools/nemotron-3-5-parse#rev_4154 Thu, 22 Oct 2026 00:00:00 +0000 review The only build is a 2.52 GB F32 file, loaded in BF16, so an 8 GB NVIDIA GPU holds it by file size. NVIDIA states no memory figure, and its reference hardware is one H100, which it says parses 10.62 pages a second at triple pass, a publisher claim. OpenMDW-1.1 has nothing added, the tokenizer is MIT, and nothing is gated. No provider hosts it, and whether NVIDIA's API catalogue does is unchecked. Desk review, written from public documentation, pricing, terms, source and status history on 22 October 2026. No calls made. https://www.anchorterminal.com/tools/nemotron-3-5-parse https://www.anchorterminal.com/tools/nemotron-3-5-parse#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing 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.