While not a model itself, this is the essential framework for the Tiny 10 movement. It allows users to run LLMs on consumer hardware using 4-bit quantization.
Gemma is Google’s contribution to the open-weights community. It is built from the same technology as Gemini.
The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. Fully open-source and highly compact. tiny 10 github top
One of the best "tiny" models for non-English languages. 9. BitNet (1-bit LLMs)
Running sophisticated AI on a Raspberry Pi or a phone. 📈 Future Outlook While not a model itself, this is the
Eliminating the need for cloud-based APIs. 🏆 Top Tiny 10 Repositories on GitHub 1. llama.cpp (The Foundation)
This GitHub project explores models where weights are just -1, 0, or 1. It is built from the same technology as Gemini
This compact model by Stability AI is focused on being a "helpful assistant." Local chatbots that don't require a GPU. 8. Qwen-1.8B (Alibaba)
Dramatically reduces energy consumption and memory usage. 10. MLC LLM
Perfect for mobile apps and low-power edge devices. 4. Google Gemma (2B Variant)