MTCode Server
The desktop controller stores credentials, downloads selected models, configures the local server, starts and stops it, and publishes its TCP endpoint to authorized DirectLink users.
MTCode AI Servers—MTCode-LLM and MTCode-Diffusion—are designed for people who want to get a useful local model running without first learning the broader AI tool ecosystem. MTCode Server provides a guided, easy-to-navigate interface for selecting and downloading models, running both servers, and securely publishing them through DirectLink.
A guided local AI setup
Instead of beginning with model formats, inference flags, and a long catalog, start with an application category. MTCode Server presents a preselected set of open-weight models hosted on Hugging Face, along with quantization and runtime choices intended to make the tradeoff between capability, speed, and GPU memory easier to understand.
Three pieces, one workflow
The desktop controller stores credentials, downloads selected models, configures the local server, starts and stops it, and publishes its TCP endpoint to authorized DirectLink users.
A local language and multimodal model server using the llama.cpp inference engine. It supports the text, coding, vision, and audio-oriented model choices exposed by MTCode Server.
A local image generation and editing server using the stable-diffusion.cpp engine. MTCode Server organizes supported workflows into generation, generation-and-editing, and inpainting categories.
Quick start for new users
A gaming PC with a GPU that has 8 GB of memory or more can run a capable local AI server for chat or image generation. The more memory the GPU has, the larger the model it can host and the higher the quality of the results. Click here to view an image generated by an NVIDIA GeForce GTX 1080 with 8 GB of VRAM, loaded with a 3.8 GB SDXL 1.0 model.
MTCode-LLM: a guided, easy-to-navigate interface for choosing and running language models.Click the image to enlarge.
MTCode-Diffusion: a guided, easy-to-navigate interface for choosing and running image models.Click the image to enlarge.
Where it fits
Ollama, LM Studio, and established image-generation tools have broader ecosystems, integrations, catalogs, and community workflows. MTCode-LLM and MTCode-Diffusion are not presented as replacements for those tools. Their advantage is a smaller, guided path from selecting a useful open-weight model to running and sharing it from the MTCode Server GUI.
Use the built-in servers when application categories and a curated shortlist are more helpful than evaluating every runtime and model independently. They provide a practical starting configuration that can be refined later.
Keep it. MTCode Server can publish any TCP service, including an existing Ollama, LM Studio, or other compatible endpoint. DirectLink does not require the service to use an MTCode inference engine.
Models are published and licensed by third parties. Review each Hugging Face model card and license before downloading the model or sharing access. MTCode-LLM and MTCode-Diffusion can run independently for local use without an MTCode account; an account is needed only when publishing through DirectLink.
MTCode Server provides a direct route from local GPU hardware to a running language or image model—and an equally direct route for authorized users to reach it.
