Fine-Tuned Models — GNO

Fine-tune the AI models that power GNO’s search and answer quality. Train locally on Apple Silicon, benchmark against the baseline to prove the improvement, and ship the result as a portable model file.

Install GNO Read the docs

Use cases: Researchers iterating on retrieval quality; Teams that need reproducible, measurable gains; Open-source contributors training and publishing retrieval models

What it gives you

Train locally on Apple Silicon — no cloud GPU required
Automatic best-checkpoint selection
Portable model export (GGUF format)
Benchmark against the shipped baseline before switching
Published reference model on Hugging Face for community use
Automated model candidate search with bounded budgets

Try it yourself

Representative commands and entry points. Full reference lives in the documentation.

gno models use slim-tuned

gno models pull --gen

gno query 'topic' --thorough

Keep reading

Related features and docs.

Benchmarks

/features/benchmarks

Local LLM answers

/features/local-llm

Fine-tuned models reference

/docs/fine-tuned-models

All features

Back to the feature index