The Local LLM Index / Quantization & Formats / #59

Helldez/BigMoeOnEdge

by Helldez · Quantization & Formats · updated 4d ago

Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, CPU only, lossless, on stock llama.cpp

68
momentum
554
stars
58
forks
#59
rank
androidcppedge-aigemmaggufgpt-ossinferencellama-cppllmmixture-of-expertsmoeon-device-ai
View on GitHub →