Q
QuantaLLM
Intelligence. Powered by Your Handhelds. Anywhere
4.5(10,000 avis)
Gratuit
Lancé en 2026
Sobre
Run large language models entirely on your Android phone. Powered by llama.cpp with Hexagon NPU acceleration and ONNX Runtime — 100% offline, fully private inference on ARM64.
Points positifs
- +Execução de modelos de linguagem de grande escala em seu telefone Android
- +Aceleração com Hexagon NPU e ONNX Runtime
- +100% offline e privado
Points négatifs
- −Limitado a ARM64
- −Dependência de recursos do telefone
