llm 54 llama 53 ai 48 nodejs 46 cuda 32 gguf 31 vulkan 31 metal 31 bindings 30 prebuilt-binaries 30 self-hosted 30 catai 30 gpu 29 embedding 29 grammar 29 cmake-js 29 cmake 29 function-calling 29 json-schema 29 llama.cpp 23 llamacpp 19 Local LLM 18 node-js 16 native 15 genai 14 arm64 8 x64 7 linux 6 local 5 win32 5 react-native 5 deepseek 4 darwin 4 llama-2 4 LLM 4 large language model 4 android 4 ios 4 raspberry-pi 4 openai 4 json-grammar 3 json-schema-grammar 3 hugging-face 3 speech-recognition 3 temperature 3 topK 3 topP 3 ollama 3 mistral 3 typescript 3 zhipu-ai 2 whisper.cpp 2 writer 2 watsonx-ai 2 voyage-ai 2 node-addon 2 together-ai 2 theb-ai 2 shuttle-ai 2 replicate 2 reka-ai 2 perplexity-ai 2 octoai 2 chatbot 2 qwen 2 qwq 2 lora 2 seed 2 minP 2 speculative-decoding 2 token-prediction 2 batching 2 functions 2 reranking 2 rerank 2 whisper 2 audio 2 transcription 2 voice-activity-detection 2 vad 2 cpp 2 chatgpt 2 llm-interface 2 ai21-studio 2 ai21 2 ailayer 2 aimlapi 2 anyscale 2 anthropic 2 microsoft-azure-ai 2 cloudflare-ai 2 cohere 2 corcel 2 deepinfra 2 fireworks-ai 2 forefront-ai 2 friendliai 2 google-gemini 2 neets-ai 2 gooseai 2