llm 65 llama 59 ai 54 nodejs 47 self-hosted 35 cuda 34 gguf 34 function-calling 33 json-schema 33 metal 33 vulkan 33 bindings 32 prebuilt-binaries 32 cmake-js 31 embedding 31 gpu 31 cmake 31 catai 31 grammar 30 llama.cpp 27 llamacpp 21 Local LLM 19 native 18 inference 17 node-js 17 genai 15 beam-search 14 test-time-scaling 14 ollama 10 openai 10 typescript 9 arm64 9 x64 7 linux 7 cli 7 local-llm 7 local 7 claude 6 vllm 6 deepseek 6 mistral 5 tool-calling 5 ai-agents 5 raspberry-pi 5 win32 5 android 5 ios 5 react-native 5 gmail 4 jira 4 automation 4 github 4 slack 4 json-grammar 4 json-schema-grammar 4 temperature 4 topK 4 topP 4 darwin 4 lora 4 mcp 4 copilot 4 agentic 4 yaml 4 marktoflow 4 llama-2 4 large language model 4 LLM 4 structured-output 3 chatbot 3 workflow-automation 3 seed 3 markdown 3 model-context-protocol 3 on-premise 3 machine-learning 3 ai-automation 3 ai-workflow 3 minP 3 workflow 3 rerank 3 reranking 3 functions 3 hugging-face 3 token-prediction 3 private 3 secure 3 speech-recognition 3 gpt 3 anthropic 3 air-gapped 3 local-first 3 no-telemetry 3 gemini 3 openai-compatible 3 data-privacy 3 batching 3 qwq 3 qwen 3 speculative-decoding 3