ai-local-model-ops

# Local Model Operations Use this skill to choose and operate local or self-hosted LLM workflows when privacy, offline access, or low-friction experimentation matter more than large-cluster serving. This skill covers: - local runtime choice for laptops, workstations, and small self-hosted setups - team-facing local or private chat surfaces - single-binary or minimal-dependency model packaging - lightweight adaptation paths before full training or cluster-scale serving - evaluation and escalation rules before a local stack becomes a product dependency ## ASCII Flow ```text local/private model need | v constraint privacy | offline | cost | hardware | demo portability | team chat | v runtime selection Ollama | LM Studio | MLX | Microsoft Foundry Local | Open WebUI | llamafile | lightweight adapter workflow | v local operating contract pinned model + quantization + eval set + storage/privacy boundary + optimization levers: KV-cache quant | speculative decoding | NPU tier | v use or escalate local workflow OR hand off to inference/MLOps for production serving ``` ## Quick Reference | Need | Default path | Notes | |------|--------------|-------| | Run a local model quickly | Ollama | Lowest-friction day-0 local runtime for experiments and private workflows | | Share a self-hosted chat UI | Open WebUI | Best fit when a team needs a ChatGPT-like local or private interface | | Ship a no-install demo or portable binary | llamafile | Useful for single-fi...