facebookresearch/MobileLLM
A Facebook Research project training sub-billion parameter language models optimized for mobile and on-device inference.
Not currently ranked — collecting fresh signals.
star history
MobileLLM provides training code and models for compact language models under one billion parameters, using design choices like SwiGLU activation, deep thin architectures, embedding sharing, and grouped-query attention to maximize quality at small scale. The project has released multiple iterations including MobileLLM-R1 and MobileLLM-R1.5, with models publicly available on HuggingFace and validation across math, coding, and commonsense reasoning benchmarks.
Frequently asked
- What is facebookresearch/MobileLLM?
- A Facebook Research project training sub-billion parameter language models optimized for mobile and on-device inference.
- Is MobileLLM open source?
- Yes — facebookresearch/MobileLLM is an open-source project tracked on heatdrop.
- What language is MobileLLM written in?
- facebookresearch/MobileLLM is primarily written in Python.
- How popular is MobileLLM?
- facebookresearch/MobileLLM has 1.4k stars on GitHub.
- Where can I find MobileLLM?
- facebookresearch/MobileLLM is on GitHub at https://github.com/facebookresearch/MobileLLM.