Show HN: Qwen 3.5 running on a $300 Android phone – on-device, open source
https://github.com/alichherawalla/off-grid-mobile-ai/
Qwen 3.5 Small dropped two days ago. I had it running on a mid-tier Android phone within hours.It's great seeing the on-device AI community light up around this release. Off Grid brings it to Android: phones with 6GB RAM in the $200-300 range, ~8 tok/sec on the 2B model. Fully offline.
Text generation, vision AI, image gen, voice transcription, tool calling, document analysis — all on-device, nothing uploaded, ever. Works in airplane mode.
780+ GitHub stars. ~2,000 downloads across Android and iOS. Early days.
GitHub: https://github.com/alichherawalla/off-grid-mobile-ai
Play Store: https://play.google.com/store/apps/details?id=ai.offgridmobi...
App Store: https://apps.apple.com/us/app/off-grid-local-ai/id6759299882
(
10 comments
| 3 points
| on HN
)
I've documented everything here: https://github.com/alichherawalla/off-grid-mobile-ai/blob/ma...
llama.cpp compiled as a native Android library via the NDK, linked into React Native through a custom JSI bridge. GGUF models loaded straight into memory. On Snapdragon devices we use QNN (Qualcomm Neural Network) for hardware acceleration. OpenCL GPU fallback on everything else. CPU-only as a last resort.
Image gen is Stable Diffusion running on the NPU where available. Vision uses SmolVLM and Qwen3-VL. Voice is on-device Whisper.
The model browser filters by your device's RAM so you never download something your phone can't run. The whole thing is MIT licensed - happy to answer anything about the architecture.
Could it please be improved to allow selection and copying of only the desired text?