AI that lives on your computer. Open-source, private & always local.
Run frontier AI entirely on your machine. No API keys, no telemetry, no limits. Own your models and conversation data.
curl -LsSf https://llama.app/install.sh | sh Pair it with a local coding agent.
Run llama serve, install the pi-llama plugin and launch Pi. It will automatically discover your local model. No config, no API keys. Files stay on your machine, requests never leave it.
# 1. Serve a model
llama serve
# 2. Install the pi-llama plugin
pi install git:github.com/huggingface/pi-llama
# 3. Run Pi, everything is set
pi
Optimized for any hardware.
From your laptop to a cluster, llama.cpp runs on whatever you have. Same binary, same models, same hand-tuned kernels for every GPU and CPU.
Apple Silicon
M Ultra
RTX 5090
CPU
Jetson
H100
MI300 RTX 4090
A100
M Pro
Run your first model
Qwen 3.8
Alibaba's latest multimodal reasoning models. The 27B dense model is tuned for coding, research, and long-horizon agentic work, with 256K native context.
Laguna XS 2.1
Poolside's compact mixture-of-experts model for agentic coding. Built for long-horizon work with interleaved reasoning and 256K context.
DeepSeek V4
DeepSeek's sparse mixture-of-experts line for agentic coding and reasoning. Flash is the smaller of the two, at 304B total parameters and 1M context.
Gemma 4
Google's most capable open models, built from Gemini 3 technology. Supports multimodal reasoning, agentic workflows, and 140+ languages.
GLM 4.7
Zhipu AI's agentic reasoning and coding models. Built for software engineering, browser automation, and multi-turn tool use.
GPT-OSS
OpenAI's first open-weight models since GPT-2. Built for reasoning, agentic tasks, and developer use with function calling and tool use capabilities.