Un modello 100% locale sul tuo smartphone!
Summary
A developer shares their success in fine-tuning Qwen 3 models (1.5B and 4B) for local use on smartphones, with a downloadable APK that works offline, and plans for a Windows version.
Similar Articles
Un modello linguistico locale, privato 100%, sul tuo smartphone!!
Un modello linguistico locale e privato (Qwen 3 da 1.5B e 4B quantizzati) può girare offline su smartphone, con fine-tuning e LoRA distillato da un 32B.
Un modello 100% locale, anche sul tuo smarphone!
Rilasciata un'interfaccia per gestire due piccoli modelli (4B e 1.7B) che girano localmente sullo smartphone. Il 4B funziona bene su telefoni di fascia alta; il 1.7B ha problemi di stabilità con il reasoning, in fase di miglioramento con fine-tuning approfondito usando 130k esempi e distillazione da un teacher 32B.
Got local Qwen 3.5/3.6 generating meeting summaries entirely offline on an M4 Max. Demo with Wi-Fi off. This is the future.
The Hedy meeting app now supports fully offline AI summaries using local models like Qwen and Gemma via llama.cpp, with options for bring-your-own-model and hardware-aware model selection. The update enables Wi-Fi-free operation on Apple Silicon and Windows GPUs, though cloud still offers higher speed and quality.
"Browser OS" implemented by Qwen 3.6 35B: The best result I ever got from a local model
A user reports achieving impressive results with Qwen 3.6 35B running a 'Browser OS' implementation locally, highlighting the model's capability for complex task execution without cloud dependencies.
Qwen 3.8 Flash Next locally on simple mobile phone at 3.5 tok/s
Demonstrates that Qwen 3.8 Flash Next can run locally on a mid-range Android phone at 3.5 tokens per second with optimizations and low quantization.