Llama ❤️ @huggingface Hub 🤗
Get started with thousands of LLMs with a few clicks, running lightning-fast on your computer 🦙
Private, local, open-source 🙌🏻
@si_mon_ami Not on the roadmap right now, but you can point it at GGUF files from LM Studio by hand, in ~/.config/llama/models.user.ini (there's an example in the file).
@the_spacebat Thanks! The app is a 1.3 MB download (4.4 MB installed). If you don't already have llama.cpp, it sets it up on first launch, which is another ~24 MB.
@vulnerablecodes No need for the command line -- the app starts and manages the server for you.
Common settings are in the GUI (context size, port, network access). Any other llama.cpp option you can set per model in ~/.config/llama/models.user.ini
@growaiskills Good point. Memory depends on the context length you pick, so the model page shows it per context once downloaded -- e.g. gpt-oss-20b: 12 GB at 8k, 15 GB at 128k. At the default context it's close to the file size, and the Recommended list only shows models that fit your Mac.
@dmytrovirych It only recommends models that fit your Mac, so it adapts to what you have. Rough guide: 16 GB for small models like Gemma 4 E4B, 24 GB+ for gpt-oss-20b, 32 GB+ for Qwen3.8-27B.
llama.cpp now has an official website: https://t.co/vztdUpdBWL
Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.
While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).
We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.