标签：Apple Silicon

Self-hosted DeepSeek-OCR-2 WebUI & API — vLLM / transformers on NVIDIA, Apple Silicon & CPU, per-page quality checks, PDF streaming, MCP

A small, quiet system monitor for Apple Silicon Macs: one floating glass panel that works at any size.

Phosphene is a free, open-source Mac app for making AI videos, pictures, speech and songs offline. Run LTX-2.5 and MiniMax H3 (Hailuo) locally on Apple Silicon: text-to-video and image-to-video with sound, lip-sync, character LoRA training. Mac app or Pinokio. No cloud, no API key, no NVIDIA GPU. Works with Claude Code, Codex and any MCP agent.

W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA speedup, built as MLX custom primitives.

'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and other APIs running on your Mac through a single aggregated OpenAI-compatible API endpoint. Supports Apple Vision and single command (non-server) inference with piping as well . Now with Web Browser and local AI API aggregator

High-performance lightweight proxy and load balancer for LLM infrastructure. Intelligent routing, automatic failover and unified model discovery across local and remote inference backends.

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

macOS 菜单栏极简性能监测工具

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

The production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/Anthropic/Ollama-compatible endpoints, a built-in chat UI, and native MCP.

Phi-3, -3.5, and -4 for Mac: Locally-run Vision and Language Models for Apple Silicon

Your AI intranet: network the computers you already own for inference and training.

Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.

Native macOS menu-bar monitor for CPU, memory, and disk, with reviewed cleanup for caches, builds, simulators, and AI agents. Local and open source.

把 Mac 刘海变成随手可用的本地工作台：待办、随笔记、链接、录音与 AI 完成提醒。

Translate entire books with AI you already have.

Kyojin: open-source engine that runs 100 GB-class open models (GLM-5.3, Qwen3.8, DeepSeek V4.1) on one desktop machine. AMD Strix Halo, NVIDIA RTX and Apple Mac. OpenAI API, built on ExLlamaV3.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.