Les conversations de vos utilisateurs ne quittent jamais le téléphone.
Exécutez des LLMs sur Android avec une ligne Gradle. Chat, complétion, embeddings, modèles GGUF — on-device, sans cloud, sans clé API, sans facturation par token. Privé par design, fonctionne hors-ligne, inférence temps réel.
// llama.cpp · GGUF models · arm64-v8a · API 24+ · Android 15 ready · 16 KB aligned
Les APIs LLM cloud voient tout ce que vos utilisateurs tapent.
Every prompt sent to ChatGPT, Claude, or Gemini APIs leaves the phone. For health, legal, financial, or personal use cases — that's a dealbreaker. On-device LLM runs locally: nothing uploaded, nothing stored, nothing billed per token. Private, offline, zero latency to a server.
Chattez gratuitement. Passez au Pro pour le GPU et le streaming.
La version gratuite vous donne l'inférence LLM complète sur CPU. Le Pro ajoute l'accélération GPU Vulkan (significativement plus rapide sur les SoC modernes), le streaming de tokens via Kotlin Flow, et le support multi-session concurrent.
- llama.cpp prebuilt · CPU ARM NEON optimized
- Chat completion (prompt → response)
- Embeddings (text → vector)
- System prompts + chat templates (auto-detect)
- All GGUF models (Llama, Qwen, Phi, Gemma...)
- arm64-v8a · single session
- Everything in Free
- Vulkan GPU acceleration — faster on Snapdragon, Exynos, Tensor
- Streaming tokens via Kotlin Flow (word by word)
- JSON / Grammar mode — force structured output (GBNF)
- Vision / Multimodal — image + text input (LLaVA, Llama Vision)
- Context save/restore — resume conversations after app kill
- LoRA adapters — specialize models without retraining
- Function calling / tool use — structured agent actions
- Concurrent multi-session (shared model, isolated KV caches)
- arm64-v8a + x86_64 (emulators, Chromebooks)
Téléchargé séparément — choisissez celui qui correspond à votre app.
Models are not bundled in the AAR (too large, 400 MB to 8 GB). Download a GGUF model from HuggingFace and ship it with your app or download it at first launch.
Sans NDK. Sans Python. Sans scripts de build. Ajoutez la dépendance.
The prebuilt AAR includes the compiled libllama.so and the Kotlin API. Add one line to your build file, download a model, chat.
Forcez la sortie JSON. À chaque fois. Garanti.
Cloud APIs sometimes return malformed JSON. On-device LLMs are worse — unless you constrain them. Grammar mode forces the model to generate structurally valid output, defined by a GBNF grammar. JSON, XML, custom formats — if you can define it, the model will follow it.
Envoyez une image. Obtenez une réponse.
With multimodal GGUF models (LLaVA, Llama 3.2 Vision), the Pro tier accepts image + text input. Describe photos, read receipts, analyze screenshots — all on-device, no cloud upload.
Android a tué votre app. La conversation survit.
Android aggressively kills background apps to free memory. Without context persistence, every return to the app restarts the conversation from zero. Pro saves the KV cache to disk — the conversation resumes instantly, exactly where it left off.
Les tokens arrivent mot par mot. Comme ChatGPT.
The free tier returns the complete response at once. Pro streams tokens via Kotlin Flow — your UI updates in real time as the model generates, exactly like a cloud chat UI but running locally.
Assistant vocal. Entièrement sur l'appareil.
Pair llama.cpp with Whisper for a complete voice AI pipeline. Whisper transcribes speech, llama.cpp generates the response, Android TTS reads it aloud. No cloud, no API, no subscription — a full assistant running on the phone.