# Ollama Architecture and GGUF Memory-Mapping > Source-anchored research for Ollama Architecture and GGUF Memory-Mapping. Run status: COMPLETED. Parent: [Local Model Performance Evaluation: Ollama, MLX, and Hardware Architectures](https://llms-explorer.com/tree/local-model-performance-evaluation/) · 2 facets · 4 facts · page: https://llms-explorer.com/tree/ollama-architecture-and-gguf-memory-mapping/ ## How it works - When KV cache size exceeds available headroom during extended context ingestion, Ollama dynamically reallocates context buffers, incurring allocation stalls unless context size is pinned via num_ctx in Modelfile. (high confidence) — [source](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) ## Facts and statements - GGUF format structures model weights into contiguous tensor buffers aligned to 32-byte boundaries, enabling zero-copy mmap() loading directly into virtual memory pages. (high confidence) — [source](https://github.com/ggerganov/llama.cpp/blob/master/docs/gguf.md) - On Apple Silicon macOS, Ollama orchestrates llama-server instances allocating shared Metal command buffers, mapping unified memory buffers without host-to-device PCIe serialization. (high confidence) — [source](https://github.com/ollama/ollama/blob/main/docs/modelfile.md) - Quantization schemes such as Q4_K_M and Q8_0 balance tensor weight compression against perplexity degradation by utilizing mixed precision blocks for attention projection matrices. (high confidence) — [source](https://github.com/ggerganov/llama.cpp/blob/master/docs/gguf.md)