Open-weight models, on your terms
GraphLogic also supports open-weight models running on your own infrastructure. Use Llama, Mistral, Qwen, DeepSeek, Gemma, or Phi via Ollama, vLLM, llama.cpp, or LM Studio. The same reasoning patterns, with the model where you want it.
Compatible runtimes: Ollama, vLLM, llama.cpp, LM Studio, and any OpenAI-compatible local endpoint.