Packages for keyword “mlx”
These packages are available as a package collection, usable in Xcode or SwiftPM.
mlx-swift
Swift API for MLX
Qwen3Speech
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
mlx-libraries
Examples using MLX Swift
mlx-audio
A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
MLXAudio
A modular Swift SDK for audio processing with MLX on Apple Silicon
AgentRunKit
Swift 6 agent SDK: type-safe tools, streaming, cloud + on-device inference via MLX on Apple Silicon
CoreMLLLM
Run LLMs on Apple devices with CoreML, optimized for Apple Neural Engine + GPU
Conduit
🦑 Unified Swift SDK for LLM inference across local and cloud providers
LocalLLMClient
Swift package to run local LLMs on iOS, macOS, Linux
ManifoldKit
Reusable SwiftUI chat framework for local and cloud LLM inference on Apple platforms
SwiftSci
SwiftSci is a native, high-performance, modular data analysis and machine learning library for Swift.
SpeakSwiftly
(WIP; Rework at some point...) Local TTS and Text Processing for macOS
GLiNER2Swift
Swift port of Gliner2 framework
PrivateFoundationModels
Apple FoundationModels API on iOS 18+. Same call site, native passthrough on iOS 26 (Apple Intelligence), CoreML / MLX backends on older OSes. Drop-in source compatible.
SemanticSearch
On-device semantic search for Apple platforms via MLX
ModelRelay
Composable AI workflows for Swift: small typed steps, a model per step, tools, MCP and on-device models.
OpenJevSwift
Native Swift implementation of OpenJev, the Jev-compatible typed-decision server: yes/no, choice and score answers read from model probabilities, on Apple silicon Macs and in iPhone apps. Serves Verdict, Laya, DiffusionGemma and JevK5. Apache-2.0.
VeloxQuant
Swift SDK for VeloxQuant (Apple Silicon MLX KV-cache compression) — sibling to the TS, Go, Rust, and Kotlin client SDKs.
Cast
Type-safe structured output from any local LLM on Apple Silicon. Constrained decoding for MLX Swift.
FiniteExtract
On-device structured extraction engine (Swift Package)