Fetches just the Q4_K_M GGUF file of the Llama-3.2-1B model into ./llama32. GGUF is a quantized (compressed) model format designed for CPU inference, and Q4_K_M is the popular quality/size sweet spot. Ollama-style runners and llama.cpp load these files directly, so this is how you fetch a model for CPU-only setups.
Looking for more? Search all 7,657 commands — works offline, in English or Spanish, and fixes typos.