CompareOpen in App Store
★★★★★
Average rating on the App Store. Apple doesn't publish how many ratings each star has.
This app isn't in any of our charts yet.
Replies start instantly in long chats, photos included. Long chats keep your first message and the system prompt. A short default system prompt you can read and edit. Replies stop at 512 tokens, with a Continue button. A notice when the phone runs hot, with a lighter model suggestion. My Models: every download in one place, with sizes. Report a problem by email, straight from the app. Import explains up front when a model will not fit. Tap your message to see its image and the exact prompt.
Pocket AI Lab scans your device, tells you honestly which models will actually fit, downloads them straight from Hugging Face, and lets you chat with them fully offline. Multi-backend inference - MLX, llama.cpp (GGUF), Core ML, and Apple Intelligence, switchable at runtime Multimodal - text, images and video frames (vision models), speech-to-text (Whisper) Import any model by link - paste a Hugging Face URL, pick a quantization, get a fit verdict before a single byte downloads Honest memory budgets - recommendations are computed from the real per-process memory limits of your device, not marketing RAM numbers Live metrics CPU, RAM and thermal pressure while the model is thinking Streaming chat token-by-token, with full conversation history on every backend