LocoLLM Documentation
Frontier AI on a budget. Crazy, right?
LocoLLM is an open-source experiment in building routed, task-specific language models that run entirely on consumer hardware. One base model, many specialist adapters, zero cloud dependencies.
Getting Started
Section titled “Getting Started”Understand the project’s goals, hardware, and philosophy.
Why LocoLLM · FAQ · Meet the Lab
Guides
Section titled “Guides”Hands-on guides for training adapters, benchmarking, and evaluation.
Adapter Guide · Adapter Primer
Reference
Section titled “Reference”Architecture decisions, model selection rationale, and research direction.
Architecture · Research Roadmap · Architecture Vision
Benchmarks
Section titled “Benchmarks”Interactive results: quality, speed, and efficiency across 14 models x 8 quant levels.
Contribute
Section titled “Contribute”Project ideas for capstone students and contributors.
Decisions (ADRs)
Section titled “Decisions (ADRs)”Recorded technical decisions and the reasoning behind them.