







A local inference engine for Apple silicon, built around the model. - incoai/splash
Optimizing On-Device Inference for Apple Silicon
A custom local engine that improves prefill and decode throughput

Part 4: Brief history of Apple ML Stack
By Mirai Labs, frontier on-device AI lab. Building the models, inference runtime, and quantization stack from the device constraint up.

Mount Thor — AI Execution Environments on Apple Hardware
Managed macOS environments for AI workloads that require native desktop access, persistent state, or model inference on Apple silicon.

Osaurus — Own Your AI on Apple Silicon
Own your AI: local-first agents with memory, tools, and identity on Apple Silicon. Offline, open source, and API-compatible with OpenAI, Anthropic, and Ollama.

Osaurus — Own Your AI on Apple Silicon
Own your AI: local-first agents with memory, tools, and identity on Apple Silicon. Offline, open source, and API-compatible with OpenAI, Anthropic, and Ollama.

Apple has new Mac app coming to make running local AI models easy
Leaker Aaron Perris has discovered evidence of a new Mac app in the works at Apple that makes it easy to run local AI models.

raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
raullenchai/Rapid-MLX
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Locally AI - Run AI models locally on your iPhone, iPad, and Mac.
Run Llama, Gemma, Qwen, DeepSeek, and more on your iPhone, iPad, and Mac. Optimized for Apple Silicon. Offline. Private.

oMLX — LLM inference, optimized for your Mac
Native macOS inference server built on MLX with paged SSD KV caching for Apple Silicon.

apple-silicon-llm-bench/results/complete_results.html at main · AlexHiesch/apple-silicon-llm-bench
Systematic LLM inference benchmark for Apple Silicon: 8 backends, 7 models, 791 measurements - AlexHiesch/apple-silicon-llm-bench
Making Apple Neural Engine work in a custom inference stack
Apple Neural Engine always looked appealing on paper, but using it inside a custom runtime was harder. In 1.20260410.1, we made ANE practical for 8-bit S models by using CoreML only as an accelerator.

Rohan Paul on Twitter / X
👨🔧 Github: Native, Apple Silicon–only local LLM server. Similar to Ollama, but built on Apple's MLX- OpenAI API compatible, - Ollama‑compatible- OpenAI‑style tools + tool_choice, with tool_calls parsing and streaming deltasgithub. com/dinoki-ai/osaurus pic.twitter.com/G0NbWnEJcQ— Rohan Paul (@rohanpaul_ai) September 3, 2025

AppleScript-8B & AppleScript-16B: Small Models That Actually Drive Your Mac — Osaurus
Two open models that turn plain-English requests into working macOS automation — on-device, tool-calling, quantized for Apple Silicon.

AppleScript-8B & AppleScript-16B: Small Models That Actually Drive Your Mac — Osaurus
Two open models that turn plain-English requests into working macOS automation — on-device, tool-calling, quantized for Apple Silicon.
