coreai-modelsApple's official Core AI toolkit: recipes exporting Hugging Face models to .aimodel, PyTorch primitives for authoring, Swift runtime for macOS/iOS apps — plus skills for coding agents.
Why switchBoth put models inside macOS/iOS apps through a Swift runtime; Apple's Core AI exports Hugging Face models to .aimodel, uzu runs its own Metal engine with a ready model catalog and chat/tool-call API.
Full comparison → xybridCross-platform on-device AI toolkit: run LLMs, ASR and TTS natively from Flutter, Unity, Kotlin, Swift or Rust on a llama.cpp and ONNX Runtime core. Private, offline, no cloud.
Why switchBoth are embeddable on-device inference SDKs with Swift and Rust bindings for shipping private, offline LLMs in apps; xybrid spans more platforms on llama.cpp/ONNX, uzu goes deep on Apple unified memory.
Full comparison → strands-deciderStrands' small decision model (2B, Qwen3.5-based): pick between options, answer yes/no or rate on a scale with calibrated confidence. CLI and /v1/systemone server on CUDA, MPS, MLX or CPU.
Why switchBoth serve a small decision model locally behind the TypeSafe-style /v1/systemone API with typed choice, yes/no and score answers; Strands runs on CUDA/MPS/MLX/CPU, uzu on its Metal engine.
Full comparison → OllamaRun Llama, Mistral and other open models locally with a single command and a clean API.
Why switchBoth run open models locally behind an OpenAI-compatible server; Ollama is the general-purpose daemon, uzu is meant to be embedded in your app via native bindings.
Full comparison → StrataHybrid GPU/CPU MoE engine that runs Qwen3.8-Flash-Next and DeepSeek V4.1 on consumer cards: hot experts cached in VRAM, rest computed in RAM, MTP drafting, local OpenAI/Anthropic API.
Why switchBoth run models locally behind OpenAI-compatible endpoints: Strata serves huge MoEs on a gaming GPU, uzu embeds small models inside Apple apps.
Full comparison →