Canonical AI event

Nvidia Nemotron-3.5-Parse added as supported VLM model in v2.141.0

The v2.141.0 release includes support for the Nvidia/Nemotron-3.5-Parse VLM model. It also improves performance for Word-exported ODT files.

21 Oct 20261 verified claims1 sources1 observations

What happened

The official source reports this update: v2.141.0.

Why it matters

This official update documents a development concerning v2.141.0. Its practical significance depends on the scope and evidence stated by the source.

What to watch next

Read the official source update and verify its stated scope, evidence and timing before acting on it.

Connected knowledge

Entities affected by this event

Doclingsubject

Continue this topic

agents-softwareDocling-tools v2.140.0 now prefetches Distil-Whisper presets.16 Oct 2026 agents-softwareNew version 2.139.0 adds per-page confidence breakdown in ConfidenceScores14 Oct 2026 agents-softwarePP-OCRv6 languages now supported in rapidocr's list_supported_langs9 Oct 2026 agents-softwareDocling 2.133.0 adds configurable RapidOCR model size.3 Oct 2026 agents-softwareNew version 2.128.0 of software adds NVIDIA-Nemotron-Parse-2.0 model.16 Sept 2026 agents-softwareVersion 2.125.0 adds CUDA support for RapidOCR ONNX Runtime.3 Sept 2026

Evidence trail

Sources behind the event

Docling official releasesv2.141.020 Oct 2026

Editorial presentation

Read the public story