Llama

AI that lives on your computer. Open-source, private & always local.
From the team at Llama.cpp and Hugging Face.

[Llama @Llama_app]

@yangzhizheng1 @huggingface We have plans for mobile!

[Llama @Llama_app]

Llama ❤️ @huggingface Hub 🤗

Get started with thousands of LLMs with a few clicks, running lightning-fast on your computer 🦙

Private, local, open-source 🙌🏻

[Llama @Llama_app]

Llama takes voice, images, video inputs simultaneously 🗣️

Hit record, ask your question out loud, drop in a photo, let it answer lightning fast. All running locally on your machine.

We recommend LFM3-Omni @liquidai cutting-edge multimodal intelligence on your computer 🦙

[Julien Chaumond @julien_c]

One of the coolest recent features in Pi is Virtual Models

I am using it to route to Qwen 3.8 27B (running locally in @Llama_app) or to Kimi K3 or GLM 5.3 (hosted remotely),
depending on my query complexity and my machine's current load 🔥

No more manual model switching!!

Kudos @badlogicgames @mitsuhiko + ggml team!!

[Llama @Llama_app]

Llama integrates to your favorite coding agents through their onboarding 🦙

Let your agents work offline: anywhere, anytime, keep your private info locked on your computer 🔒

Point your agent to this doc to set it up https://t.co/2ZGBNlBucL

[Llama @Llama_app]

@thesignalnow It is offline inference, as in, no need to have internet to run an agent.

[Llama @Llama_app]

Llama integrates to your favorite coding agents through their onboarding 🦙

Let your agents work offline: anywhere, anytime, keep your private info locked on your computer 🔒

Point your agent to this doc to set it up https://t.co/2ZGBNlBucL

[Llama @Llama_app]

Get started with Llama with a single click 🦙https://t.co/8IN1wd8iTB

[Llama @Llama_app]

Run decision models locally with a single click, get answers lightning-fast ⚡️

Llama now supports d1-Omni by @liquidai for multimodal queries, as well as d3-flash by vLLM, leading Jev Decision Index 🤝

Update Llama today 🦙

[Llama @Llama_app]

@geron_labs @llama_cpp llama.cpp exists, Llama is the platform agnostic desktop app on top to lower barrier of entry to run local to millions of people, building on llama.cpp!

[Llama @Llama_app]

Own your intelligence 🤝 with only a few clicks!

[Emanuil Rusev @erusev]

I've been building Llama with the llama.cpp team — a tiny menu bar app that runs open models on your Mac.

Here it is in 35 seconds 🦙

[Llama @Llama_app]

@ItsmeAjayKV @llama_cpp It's @llama_app, we have moved from @llama_cpp, you can check out the bio of latter!

[Alex Cheema @alexocheema]

frens at Hugging Face tell me llama app (llama.cpp) has a new home: @Llama_app

Follow & spread the word!! 🤗🦙

[Llama @Llama_app]

@robertomasymas @llama_cpp We have moved from llama_cpp, you can see in the bio!

[Llama @Llama_app]

Our picks from last week's model drops 🦙

→ LFM3 by Liquid AI: small models for text, image and speech, with d1 decision models
→ Mistral Large 4: large, 1M context frontier
→ Flint by Recursive: mid-sized, built for coding agents

Get them at https://t.co/dshhEJyjtm

[Cee @Cee_Momma]

Everyone please be careful at raves my home girl smoked a guys blunt that was laced with fentanyl she went to the hospital and was having seizures. Please be safe tonight 🙏🏽