#ollama

llmfit is an open-source CLI tool that automatically detects your system's RAM, CPU, and GPU specs to recommend the optimal LLM model and quantization level, dramatically lowering the barrier to running local AI.

Ollama 0.17, released February 22, introduces a new native inference engine replacing llama.cpp server mode, delivering up to 40% faster prompt processing and 18% faster token generation on NVIDIA GPUs, plus improved multi-GPU tensor parallelism and AMD RDNA 4 support.