262+ curated AI tools and growing

llama.cpp

Local LLM inference engine running GGUF models on CPU/GPU.

API & ModelsLocalOpen source

About this tool

llama.cpp Local LLM inference engine running GGUF models on CPU/GPU.

A go-to option in API & Models, llama.cpp suits individuals and teams via its website or API integrations.

Groq LPU inference with ultra-fast Llama and open models via API.

CLI to run open LLMs locally for self-hosting and developer integration.

Self-hosted open chat UI for Ollama and OpenAI-compatible APIs.

Unified API gateway to call GPT, Claude, Llama, and hundreds of models.