metal

10 projects share this GitHub topic

Lines connect members that are measurably related to each other. Dot size reflects stars.

🧬 Members

turbo-fieldfare

Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model…

A high-performance inference engine for AI models

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

Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG

Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple…

metal-flash-attention

FlashAttention (Metal Port)

A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based…

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache…

Core-AI-Framework-Lab

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device…

🔗 Related families

apple-silicon 37 on-device-ai 24 cuda 78 llama-cpp 23 gemma 30 gemma4 9 local-ai 45 gguf 21

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.