Blog

Articles, guides, and insights on local artificial intelligence

Sort articles by:Newest Oldest Title (A-Z)Title (Z-A)

All Comparisons Use cases Models Fundamentals Hardware Guides Privacy

Level:All Beginner Intermediate Advanced

1 article found per "llama-cpp"

KV cache: why your RAM needs more than just the model

What the KV cache is, the formula to calculate it with real numbers from Llama 3.1 8B and Qwen3 8B, and the three levers to manage it: context, quantization and flash attention.

iaLocale TeamOctober 1, 2026