Prebuilt llama.cpp AAR for Android — on-device LLM inference (chat, completion, embeddings), no NDK, no cloud, no API key. GGUF models, arm64-v8a, API 24+.
Artifacts using Llama Android (1)
Maven Central search alias → dev.ffmpegkit-maintained:llama-android. Prebuilt llama.cpp AAR for Android — on-device LLM inference (chat, completion, embeddings), no NDK, no cloud, no API key.
Last Release on Jul 12, 2026
- Prev
- 1
- Next