Show HN: Llmpm – NPM for LLMs
llmpm.conpm for LLMs — install, run, and share AI models.
We’ve built llmpm, a CLI tool that makes open-source LLMs installable like packages.
llmpm install llama3 llmpm run llama3
You can also package models with your projects so others can reproduce the same setup easily.
Website: https://llmpm.co
GitHub:https://github.com/llmpm/llmpm-dev Hi HN! We have built llmpm, a CLI package manager for open source LLMs. You can now download and run 10,000+ free models using single command. The idea came from the friction we kept seeing when trying to run models locally. Setting up models often involves downloading weights, configuring runtimes, and figuring out which models are actually good for a given task. With llmpm the goal is to make models installable like packages: llmpm install llama3 llmpm run llama3 We’ve also been working on the ability to package models with applications, so projects can declare model dependencies and reproduce the same setup easily. Alongside the CLI, we’ve been experimenting with a model ranking and benchmarking tool on the website to help developers compare models across benchmarks and choose the right one before installing. Check out rankings at: https://llmpm.co/rankings Tried this out this morning. It’s a pretty powerful CLI tool for developers working with open-source LLMs.