The Local LLM Index / Quantization & Formats / #122

jegly/OfflineLLM

by jegly · Quantization & Formats · updated 18d ago

Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection. + GPU Acceleration

55
momentum
192
stars
20
forks
#122
rank
androidandroid-aiandroid-ai-appandroid-llmartificial-intelligenceedge-aigemma4generative-aillamacppllmlocal-ailocal-llm
View on GitHub →