#metal

apache/tvm

Python

91

health

Open Machine Learning Compiler Framework

StayLameBro/backburner

Python

89

health

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

timtoole02/Camelid

Rust

89

health

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

SharpAI/SwiftLM

Swift

89

health

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache compression, MACOS + iOS iPhone app.

luigifcruz/CyberEther

C++

88

health

High-performance GPU-accelerated signal processing and visualization framework that runs anywhere.

incoai/splash

C++

88

health

A local inference engine for Apple silicon, built around the model.

carloslfu/slotstream

Swift

88

health

Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of experts) from your SSD and caches the busiest experts in memory, so it runs on Macs with 16 to 64 GB. One native Swift binary on MLX and Metal, no Python, offline. Works with Claude Code, Codex and Ollama or OpenAI clients.

CrossGL/crosstl

Python

83

health

Universal Programming Language & Translator

tenstorrent/tt-metal

Python

80

health

:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.