Android ASR Runtimes: LiteRT, ExecuTorch, and Why Your Phone Has No VRAM
You download a model from Hugging Face, but you're not downloading something that runs — you're downloading weights. Something has to map every operator onto your phone's silicon, and on Android that layer is fragmented across LiteRT, ONNX Runtime Mobile, ExecuTorch, and llama.cpp. This episode digs into why there's no VRAM equivalent on a phone, what a TPU actually changes, and how to find an ASR model on Hugging Face that won't crash your device. Plus: practical tips on tags, quantization, operator compatibility, and why a 95% TPU-accelerated graph can still be bottlenecked by the 5%…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.