FreeWeights

Run LLMs locally. Chat never leaves your device.

Checking WebGPU

Resources

GPU access Checking...
Storage used Checking...
VRAM usage No model loaded
Model status Idle
Context usage estimate Estimated
Conversation Reply budget

Selected model

Choose a model

Pick a WebLLM-compatible model from the catalog. Set a hardware profile for compatibility guidance.
Select GPU first
Cache -
Estimated memory -
Profile guidance -
Load time -
Params -
Context -