huggingface/smollm
Hugging Face's family of compact open-source language and vision models with fully open weights and complete training details.
Not currently ranked — collecting fresh signals.
star history
SmolLM is a series of efficient, on-device capable AI models from Hugging Face spanning text and vision modalities. SmolLM3 is a 3B parameter language model trained on 11T tokens that achieves state-of-the-art results at its scale while supporting multilingual input across six languages and extended 128k context windows. SmolVLM is a compact multimodal model capable of processing images and text for tasks like visual QA and image description. The repository provides model weights, training configurations, and inference tools.
Frequently asked
- What is huggingface/smollm?
- Hugging Face's family of compact open-source language and vision models with fully open weights and complete training details.
- Is smollm open source?
- Yes — huggingface/smollm is open source, released under the Apache-2.0 license.
- What language is smollm written in?
- huggingface/smollm is primarily written in Python.
- How popular is smollm?
- huggingface/smollm has 3.8k stars on GitHub.
- Where can I find smollm?
- huggingface/smollm is on GitHub at https://github.com/huggingface/smollm.