AI configurations: inference, stacks, embeddings and settings
Technical settings to run or adapt a model: inference, stacks, embeddings, LoRA, RAG…
Mistral 7B on a 16 GB Mac with Ollama
Ollama Modelfile to run Mistral 7B Instruct locally on a 16 GB Mac: Q4…
Qwen2.5 7B with vLLM on a 24 GB GPU
Serve Qwen2.5 7B Instruct with vLLM on a 24 GB GPU: OpenAI-compatible API, 8k…
llama.cpp server for a GGUF model
Run any GGUF model with the llama.cpp server: OpenAI-compatible API on port…
Private chat on your documents: Ollama, Qdrant, Open WebUI
docker-compose stack for a private chat on your documents: Ollama (model),…
Minimal private AI chat: Ollama and Open WebUI
The simplest stack for a private AI chat: Ollama and Open WebUI with…
Local automations: n8n and Ollama
docker-compose stack to automate with a local AI: n8n (workflows) and Ollama…
nomic-embed-text embeddings locally with Ollama
nomic-embed-text for a 100% local English RAG with Ollama: 768 dimensions, long…
BGE-M3 embeddings for RAG over long documents
BGE-M3 for RAG over long documents: 1024 dimensions, up to 8,192 tokens, 100+…
What is a configuration for AI?
A configuration gathers the technical settings that run or adapt a model: LoRA training parameters, a RAG pipeline, an embedding model, local inference, a stack of services, a reward function or a synthetic data recipe. You copy it and run it again to get the same result.