
Search models on Hugging Face, download them in one click, and run them locally.
No cloud. No complexity. No compromise.
http://localhost:8080/v1/chat/completionsBrowse thousands of GGUF models from the app. Sorted by downloads, filterable by size.
Download any model instantly. Resume interrupted downloads. Real-time progress tracking.
Tasmania configures llama.cpp automatically. Port, context size, GPU layers — all handled.
Drop-in replacement for any tool using the OpenAI protocol. Zero code changes.
No cloud, no accounts, no telemetry. Your data never leaves your machine.
Built-in MCP server connects Tasmania directly to Claude Code for local AI workflows.
Find models on Hugging Face directly from Tasmania. See sizes, quantizations, and popularity at a glance.
Click download. Tasmania handles everything — the transfer, the file organization, the configuration.
Hit start. Your model is running locally with a full OpenAI-compatible API. That’s it.