ai-model-selection

name	ai-model-selection
description	Use when choosing or changing the actual model for an AI feature in a BRICKS app — which GGUF, which quantization, which size — and when checking whether target devices can run it. Encodes hardware sizing rules - RAM budgets (the llm/GGML generator requires devices with more than 8GB RAM), acceleration per platform (Metal on M1+/A17+, OpenCL on Adreno 700+, Hexagon NPU on Snapdragon 8 Gen 1+, Vulkan/CUDA on desktop, WebGPU on web), context-length vs memory trade-offs, and quantization ladders. Uses the huggingface_search / huggingface_select tools to inspect GGUF metadata before committing, and lists starter models proven in BRICKS bundles (BricksDisplay/whisper-ggml for STT; Qwen 2.5 0.5B/1.5B, Gemma 2 2B class for constrained devices). Also covers when a cloud model is the better call. Triggers on "which model", "will this run on the device", "the model is too slow / too big", "pick a GGUF". Do NOT use for choosing generators (use ai-generators) or for the CTOR editor's own chat model.
license	MIT
metadata	{"version":"0.1.0","author":"BRICKS"}

Model & Hardware Selection

Size the model to the worst device it must run on. Hardware details live in references/hardware-matrix.md; starter models in references/model-catalog.md.

Announce at start: "I'm using the ai-model-selection skill to size the model."