View available llama.cpp model configurations and check their current load status.
Apache 2.0
180,147 tools. Last updated 2026-06-06 01:32
"llama.cpp" matching MCP tools:
- Retrieve a list of available LLaMA.cpp models configured for Msty Studio.MIT
- Chat with LLaMA.cpp models by providing a model name and a list of messages. Ideal for interactive AI conversations.MIT
- Quantize a HuggingFace model to GGUF, GPTQ, or AWQ format with bit width selection (2-8). Reduces model size for deployment on Ollama, vLLM, LM Studio, or llama.cpp.MIT
- Swap to a different llama.cpp model in a running session while preserving conversation context. Unloads current model, loads the requested one, and waits for readiness.Apache 2.0
- Compile OCTAVE schema or contract into GBNF or JSON Schema constraint grammar to regulate AI model outputs.Apache 2.0
Matching MCP Servers
- FlicenseAqualityCmaintenanceGenerates beautiful Excalidraw diagrams from natural language descriptions using a local llama.cpp LLM, entirely offline.Last updated3
- Flicense-qualityCmaintenanceEnables LLMs to use llama.cpp models via MCP protocol by bridging MCP requests to an OpenAI-compatible API.Last updated
- Analyze Git repository codebases by asking questions to understand architecture, debug issues, review security, or evaluate code quality with AI-powered insights.MIT
- Identify the currently loaded llama.cpp model in an active Claude Code session to verify which model is active for inference.Apache 2.0
- Check if your local llama.cpp server is running and reachable to ensure offline diagram generation from natural language.
- Change the active LLM backend for AI task routing. Specify a backend ID to switch between different local models like Ollama, llama.cpp, or Gemini for processing tasks.