MTPLX

oMLX is an open-source LLM inference server for Apple Silicon Macs, managed through a macOS menu-bar application. It serves text, vision, OCR, embedding, and reranking models through compatible API endpoints, with model discovery and management, monitoring, continuous batching, and caching. Its caching system keeps KV cache in a hot in-memory tier and a cold SSD tier, allowing cached context to remain reusable across requests even when the conversation context changes. The project can be installed as a macOS app, through Homebrew, or from source, and includes a CLI for controlling the app-managed server. The repository states that it requires macOS 15 or later, Python 3.11–3.13, and Apple Silicon hardware.

MLX is an array framework for machine learning on Apple silicon, developed by Apple machine learning research. It provides Python, C++, C, and Swift APIs modeled on NumPy, plus higher-level packages such as mlx.nn and mlx.optimizers with PyTorch-like interfaces. Its composable transformations support automatic differentiation, automatic vectorization, and computation-graph optimization; computations are lazy, graphs are built dynamically, and operations can run on supported CPUs and GPUs using shared unified memory rather than explicit data transfers. MLX is distributed through PyPI and supports model training and deployment workflows including language-model training and generation, LoRA fine-tuning, image generation, and speech recognition.

kimi-k3-mlx is an MLX port for Apple Silicon of Moonshot’s Kimi K3 native-multimodal mixture-of-experts model. It provides a stock `mlx-lm`-compatible text model definition, a 3D video-capable MoonViT vision tower with a patch-merger projector, and an `mlx-vlm`-shaped wrapper that joins the language and vision components. The model has a 1-million-token context and uses routed and shared experts, Kimi Delta Attention, gated multi-head latent attention, Attention Residuals, latent-dimension experts, and the SiTU-GLU activation; routed experts are distributed in MXFP4 while other weights use bf16. The multimodal processor expands each image placeholder into a feature block rather than performing a same-length one-token-per-image scatter. The repository includes a streaming converter because standard `mlx-lm` conversion would materialize the multi-terabyte bf16 model, along with REAP expert-pruning scripts and expert-overlap analysis using Chinese, English, code, or mixed calibration data. It also contains vision-parity tests against Moonshot’s reference implementation. The repository states that the full model cannot run on a single Mac: even its smallest deployment tier requires hundreds of gigabytes of memory and exceeds the capacity of the largest Apple Silicon machine.

slotstream is an open-source macOS local-LLM inference engine that runs Qwen3.8-Flash-Next, a 125-billion-parameter mixture-of-experts model, on Apple Silicon Macs whose memory cannot hold the model. Implemented as a single Swift binary using MLX, it keeps the dense trunk resident and reads routed expert weights from an SSD into a shared cache of slots, sizing that cache to available memory instead of loading the full model. It supports prefix caching for follow-up turns and exposes Ollama-compatible and OpenAI-compatible chat APIs, as well as a command-line prompt mode; the documented API subset supports streaming, CORS, and sampling options but not tools, images, JSON-schema output, or logprobs. The project requires macOS 14 or later, Apple Silicon, and roughly 110 GB of free disk space for the model weights. Its installer provides signed release binaries, and the repository can also be built with Swift and the macOS Command Line Tools. The source is MIT-licensed; the model weights are distributed under the Qwen community license.

Personal Model is an open-source, local-first AI memory runtime from Intuition Lab for giving coding agents evidence-linked context about a user. After macOS permissions are granted, it captures focused activity from applications on the user's Mac and builds a portable HUMAN.md-style personal context model, storing the data locally and allowing it to be inspected, corrected, exported, or deleted. The runtime progressively organizes sourced observations and events into relationships and changes, supported patterns, higher-order structures, and an integrated current model. It retains source receipts for important claims so later evidence can strengthen, revise, or overturn inferences, then exposes this context through MCP to trusted clients including Claude Code, Codex, Cursor Agent, Claude Desktop, and other compatible tools.