- Home
- Translation apps
- NLLB-200
On the recordRead 13 Oct 202627 facts
NLLB-200
NLLB-200 · Menlo Park, California, United States · founded 2004
On the record
- Certified translations
- The model card says NLLB-200 translations cannot be used as certified translations.huggingface.co · read 12 Oct 2026
- Code license
- The repository says NLLB code and fairseq are MIT-licensed.github.com · read 13 Oct 2026
- Data and accuracy caveats
- The model card warns that personally identifiable information may not be entirely eliminated from training data and that mistranslations may remain.huggingface.co · read 12 Oct 2026
- Document translation
- Noai.meta.com · read 22 Sep 2026
- Evaluation
- Meta says it created the FLORES-200 dataset to evaluate translation quality across the supported languages.ai.meta.com · read 13 Oct 2026
- Input length
- The model card says training inputs did not exceed 512 tokens and longer sequences may have lower translation quality.huggingface.co · read 12 Oct 2026
- Integration
- Dense models are available through Hugging Face Hub and supported by the Transformers library.github.com · read 13 Oct 2026
- Intended users
- Meta presents the released models and research tools as resources for researchers and communities building or improving translation tools.ai.meta.com · read 13 Oct 2026
- Language coverage
- Meta says the model includes 150 low-resource languages.ai.meta.com · read 12 Oct 2026
- Library support
- The 3.3B model card provides usage instructions for the Transformers library and links to Google Colab and Kaggle notebooks.huggingface.co · read 12 Oct 2026
- License
- The 3.3B model card lists the license as CC-BY-NC-4.0.huggingface.co · read 12 Oct 2026
- Model license
- The repository states that the NLLB models are licensed under CC-BY-NC 4.0.github.com · read 13 Oct 2026
- Model variants
- The repository lists NLLB-200 MoE at 54.5B parameters and dense versions at 3.3B and 1.3B, plus distilled versions at 1.3B and 600M.github.com · read 13 Oct 2026
- Open-source release
- Meta says it open-sourced NLLB-200 models, FLORES-200, model training code, and code for recreating the training dataset.ai.meta.com · read 12 Oct 2026
- Purpose
- NLLB-200 is an open-source AI project with models for direct translation between 200 languages, including low-resource languages.ai.meta.com · read 13 Oct 2026
- Reported quality
- Meta reports that NLLB-200 exceeded the previous state of the art by an average of 44% in its evaluations.ai.meta.com · read 13 Oct 2026
- Repository status
- The fairseq repository was archived on March 20, 2026, and is read-only.github.com · read 13 Oct 2026
- Research resources
- The project releases model training and inference code, evaluation benchmarks, language identification models, LASER3 encoders, and data mining code.github.com · read 13 Oct 2026
