Wally
A command-line tool for downloading and running open-source language models such as GLM, DeepSeek and Qwen locally, or on hosted infrastructure when a job needs more capacity.
Wally is a command-line tool for working with open large language models. It downloads and runs models locally with commands such as wally run and wally models pull, including any GGUF model from Hugging Face, and exposes an OpenAI-compatible API with wally serve. Local models run entirely on the user's own machine; an account is only needed to use RunAnywhere Cloud for larger jobs, billed against the user's own credit.
Wally also wires up certified local models for use inside coding agents such as OpenCode and Claude Code, and ships installers for macOS, Linux and Windows. It is written in C++ and licensed under MIT.