Man pages for localLLM
Running Local LLMs with 'llama.cpp' Backend

ag_news_sampleAG News classification sample
annotation_sink_csvCreate a CSV sink for streaming annotation chunks
apply_chat_templateApply Chat Template to Format Conversations
apply_gemma_chat_templateApply Gemma-Compatible Chat Template
backend_freeFree localLLM backend
backend_initInitialize localLLM backend
compute_confusion_matricesCompute confusion matrices from multi-model annotations
context_createCreate Inference Context for Text Generation
detokenizeConvert Token IDs Back to Text
document_endFinish automatic run documentation
document_startStart automatic run documentation
dot-with_hf_tokenTemporarily apply an HF token for a scoped operation
download_modelDownload a model manually
exploreCompare multiple LLMs over a shared set of prompts
generateGenerate Text Using Language Model Context
generate_parallelGenerate Text in Parallel for Multiple Prompts
get_lib_pathGet Backend Library Path
get_model_cache_dirGet the model cache directory
hardware_profileInspect detected hardware resources
install_localLLMInstall localLLM Backend Library
intercoder_reliabilityIntercoder reliability for LLM annotations
lib_is_installedCheck if Backend Library is Installed
list_cached_modelsList cached models on disk
list_ollama_modelsList GGUF models managed by Ollama
localLLM-packageR Interface to llama.cpp with Runtime Library Loading
model_loadLoad Language Model with Automatic Download Support
model_metadataGet All GGUF Metadata from a Loaded Model
quick_llamaQuick LLaMA Inference
quick_llama_resetReset quick_llama state
set_hf_tokenConfigure Hugging Face access token
smart_chat_templateSmart Chat Template Application
tokenizeConvert Text to Token IDs
tokenize_testTest tokenize function (debugging)
validateValidate model predictions against gold labels and peer...
localLLM documentation built on Nov. 3, 2026, 1:09 a.m.