LLLM vs System26

Chat app compatible with Ollama and self-hosted models. It needs an Ollama server running and adding the endpoint in the model settings. All the information saved is local, everything is private, and no account is needed. It supports message streaming and markdown. It could also work with models served without Ollama, but that has not been tested.

System26 is a lightweight way to see device-native AI performance on your hardware. Designed for developers and enthusiasts, it surfaces on-device AI metrics across macOS, iOS, iPadOS, and visionOS. Features: • Large Language Models: Track Tokens Per Second (TPS), Latency, and Memory usage for the native System Language Model. • Image Generation: See on-device image synthesis speed using ImagePlayground with support for animation, illustration, and sketch styles. • Computer Vision: View live camera inference performance for Object Detection, Text Recognition, and Body Pose estimation. • Thermal Monitoring: Keep an eye on your device's thermal state during intensive inference tasks. • 100% Private & Offline: System26 operates without an internet connection. No data is collected, stored, or transmitted—ever. Unlock the full potential of your hardware and see how foundation models run on your machine.