Skip to content

Self-hosted

Local AI

Self-hosted models, inference hardware, runtimes, memory requirements, benchmarks and tutorials.

Friday 13 November
Thursday 12 November

17:40

Local AIAI-assisted

VRAM and large language models explained

How much memory a model really needs: weights, quantisation, the KV cache and overhead, with every figure computed by a script you can run.

17:40

Local AIAI-assisted

CPU vs GPU vs NPU for AI inference

Why memory bandwidth, not headline TOPS, sets how fast a local model talks, and where each kind of processor earns its place.

4 articles