MODEL INTELLIGENCE · SOURCE-FIRST
What is Nanonets-OCR2-3B?
Open Model Weights records Nanonets-OCR2-3B as a 3.75462B-parameter image + text → text open-weight model in the Nanonets-OCR2 family, with nanonets listed as the developer. The checked source repository provides 3 recognized weight artifacts, format evidence for Safetensors and a verified context window of 128,000 tokens. Values that are not evidenced in the checked sources remain explicitly undisclosed or unknown.
The repository declares Not declared in model-card metadata. Commercial-use status requires manual review. Open Model Weights reports the checked license evidence and classification; this is not legal advice.
Lineage metadata declares Qwen/Qwen2.5-VL-3B-Instruct as a related base model with the relation declared relationship. A training recipe and standard training-data disclosure were not found by the current verifier.
DEPLOYMENT PROFILE
Weight memory, without pretending it is a deployment guarantee.
These bars visualize weight-only decimal-GB estimates. They exclude KV cache, activations, runtime overhead, optimizer state and sharding.
LICENSE & USE
Not declared in model-card metadata
Commercial-use status requires manual review
This section summarizes the checked repository evidence. It is not legal advice.
LINEAGE & PROVENANCE
What the checked sources disclose — and what they do not.
Open Model Weights does not infer a hidden base model or training corpus when the checked sources do not declare one.
RUNTIME SIGNALS
Compatibility claims stay attached to their evidence level.
Declared and model-card-mentioned runtimes are discovery signals. They are not treated as Open Model Weights runtime tests unless explicitly measured.
EVIDENCE TRAIL
Sources and observed history.
This is where the article remains auditable: source links on one side, the registry's observed change history on the other.
Checked Hugging Face API metadata, exact repository file list, model card and config when accessible.
Previous verification level: discovered-pending.