Run MoE models bigger than your RAM. Frontier-size MoE on a phone, laptop, edge. Lossless, on stock llama.cpp. An adaptive streaming optimizer. Any hardware, any OS, any model, any quantization, behind a local OpenAI-compatible server.
Screenshots

Install
If this does not work, see FAQ#1
If this button doesn't work, see FAQ #1
How to install?
Screenshots
Sites
Sources
Exact match
Name match
Description match
No applications found
No applications found matching "{0}"
Try selecting "All architectures" or broadening your search keywords.
Check for typos or try searching with different keywords.
Clear search
{0} results
Failed to load apps.