GGiriLLM
TokensVocabularyPre-trainingFine-tuningRAGOrchestrationChat SimLocal LLM

Simulator

Set up a local LLM, step by step

Pick your hardware and operating system, choose a model that fits, generate the install commands, then wire an OpenAI compatible API and an MCP server. Every step updates a live summary on the right.

Choose a GPU

VRAM is the main limit on model size. FP16 TFLOPs drive throughput.

Step 1 of 7