Local LLM Lab

Edgy AI Labs | Hardware-aware local LLM stack advisor

Machine + Workload

Ready.

Current Hardware

No hardware loaded yet.

Recommendation

Run "Build Stack" to generate a recommendation.

Runtime Plan

Top Model Fits

Model Fit Need VRAM Need RAM Score

Distributed Probe

python -m local_llm_lab.probe_client --server http://YOUR-SERVER:8792 --name edge-box-01 --recommend --task coding