[GH-ISSUE #6981] Request to Add Support for Helsinki-NLP Models #50931

Open
opened 2026-04-28 17:34:25 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @Y-PLONI on GitHub (Sep 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6981

I would like to request adding support for the Helsinki-NLP models, specifically the ones available in this dataset: Helsinki-NLP/opus-100.

Although the current version of the software supports only GGUF files, I believe that making an exception for these models, which come in BIN format, would be beneficial. The Helsinki-NLP models are known for their high-quality translations, and they are very lightweight. This makes them an excellent choice, especially for users with low-end machines that might struggle with heavier models.

Supporting these models could significantly expand the translation capabilities while maintaining good performance, even on less powerful hardware.

Originally created by @Y-PLONI on GitHub (Sep 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6981 I would like to request adding support for the Helsinki-NLP models, specifically the ones available in this dataset: [Helsinki-NLP/opus-100](https://huggingface.co/datasets/Helsinki-NLP/opus-100/tree/main). Although the current version of the software supports only GGUF files, I believe that making an exception for these models, which come in BIN format, would be beneficial. The Helsinki-NLP models are known for their high-quality translations, and they are very lightweight. This makes them an excellent choice, especially for users with low-end machines that might struggle with heavier models. Supporting these models could significantly expand the translation capabilities while maintaining good performance, even on less powerful hardware.
GiteaMirror added the model label 2026-04-28 17:34:25 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#50931