#13 · Primary category： Foundation Models
needle
14MB foundation model for tiny devices; phones, wearables, smart home, and robots.
Project last updated：08/29/26
GitHub Stars
9.7K
Forks
622
Contributors
20
License
Apache-2.0
Why we included this project
Needle is a 26-million-parameter model built specifically for function calling on hardware that has little memory or compute. Given a natural-language request, it returns a structured tool call rather than freeform text, and that narrow focus lets it run at 1,000 to 6,000 tokens per second on phones, wearables, smart home gear, and small robots within about 14MB of weights. The open weights come with the dataset generation pipeline, so you can fine-tune it on your own tool schemas on a standard laptop. For teams prototyping on-device voice assistants or home automation, it's a concrete starting point that's small enough to actually ship.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities