Run Meta Llama, Mistral, Qwen, and other LLMs locally on CPU or consumer GPUs. The reference implementation for GGUF models.
Repository
github.com/ggerganov/llama.cppMeta
- Language
- C++
- License
- MIT
- Category
- AI Tooling
- Since
- 2023
Run Meta Llama, Mistral, Qwen, and other LLMs locally on CPU or consumer GPUs. The reference implementation for GGUF models.
Related
AI pair programming in your terminal
Chat with an LLM that can edit code in your local git repo. Maps your codebase, proposes diffs, commits when you approve. Works with Claude, GPT, DeepSeek, local models.
Open-source AI code assistant
IDE extension that lets you bring any LLM into VS Code or JetBrains. Customizable with your own models, context providers, and slash commands.
The AI coding agent built for the terminal
Terminal-native coding agent with multi-session support, LSP integration, and 75+ LLM providers. BYOK, no telemetry.