From 5eb27b5d4027e4a616f7efae8760985ca77c96b3 Mon Sep 17 00:00:00 2001 From: daniel Date: Sat, 10 Jan 2026 03:36:53 +0000 Subject: [PATCH] Update README.md --- README.md | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/README.md b/README.md index 075c1ed..9901072 100644 --- a/README.md +++ b/README.md @@ -3,7 +3,7 @@ [![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE) GT AI OS software is intended to provide easy to use "daily driver" web based generative AI for processing documents & files with data privacy for individuals and organizations. -You can install GT AI OS on Ubuntu x86, NVIDIA DGX OS 7 ARM and Apple Silicon macOS hosts using Docker. +You can install GT AI OS on Ubuntu x86 and NVIDIA DGX OS 7 ARM hosts using Docker. [Start Installation ](https://github.com/GT-Edge-AI-Internal/gt-ai-os-community/wiki/Installation) @@ -30,13 +30,10 @@ Ensure that you are using local or external inference with zero data retention f |----------|--------------| | **Ubuntu Linux** 24.04 | x86_64 | | **NVIDIA DGX OS 7** (Optimized for Grace Blackwell Architecture) | ARM64 | -| **macOS** (Apple Silicon M1+) | ARM64 | Ubuntu VM's running on Proxmox with raw all functions GPU passthrough works. Windows is currently not supported. -macoS Install scripts are designed for Apple Silicon only. - Note that the install scripts are unique for each OS and hardware architecture. Carefully choose the correct installation script for your host. @@ -48,8 +45,6 @@ We will be adjusting the installation scripts in future release so that smaller Ensure that your NVIDIA GPU hardware is physically installed prior to starting the GT AI OS installation. Note that all NVIDIA drivers and dependencies will be installed during the standard Ubuntu runbook. -There are no aditional drivers or dependencies needed for using Apple Silicon to accelerate the embedding model as that is part of the standard installation. - At v2.0.34, once you install GT AI OS, you cannot install GPU hardware and switch from CPU to GPU for embeddings. We are looking to fix this in a future release.