llama-cpp - llama.cpp Secondary LLM Inference Engine
Secondary local LLM inference engine for running GGUF models directly, loading LoRA adapters, benchmarking, and custom model serving
Tags
Updated: 2026-03-10Capabilities
Typical Inputs
Typical Outputs
What this skill does
- run GGUF inference
- load LoRA adapter
- benchmark inference
- start API server
- convert LoRA to GGUF
- resolve model path
- generate embeddings
Inputs
- GGUF model file
- LoRA adapter
- Ollama model name
- prompt text
- quantization type
Outputs
- inference text
- timing statistics
- API endpoint
- converted GGUF model
- benchmark report
Requirements
- llama.cpp installed
- GGUF model files
- Apple Silicon support