Runnable paths
Local AI execution recipes
Versioned model, hardware, tool, and workflow combinations. A recipe is separate from the planner score: it turns a compatible recommendation into steps that can be tested and reported.
Available recipes
5 reviewed pathsGenerate a Stable Diffusion 1.5 image on an Apple M-series Mac with 16GB
A conservative first-run path using Comfy Desktop, the MPS backend, the official Stable Diffusion 1.5 FP16 checkpoint, and ComfyUI's built-in image workflow.
Run Qwen3 8B Q4 locally with Ollama on a 16GB Apple Silicon Mac
A conservative Ollama path for local chat and coding experiments using Qwen3 8B Q4_K_M, Metal acceleration, a modest context window, and a repeatable API check.
Run Qwen3 8B Q4 in LM Studio on a 16GB Apple Silicon Mac
A desktop-first local chat and API path using LM Studio, a Qwen3 8B Q4_K_M GGUF artifact, Metal acceleration, and an 8K baseline context.
Run Llama 3.2 3B Q4 locally with Jan on a 16GB Apple Silicon Mac
A lower-memory desktop path using Jan, llama.cpp, Metal, and a Llama 3.2 3B Q4_K_M GGUF artifact for private chat and local API testing.
Run Open WebUI, Ollama, and Qwen3 8B on a MacBook Pro M4 16GB
A reproducible two-layer local chat stack for a 16GB M4 Mac: Ollama loads Qwen3 8B Q4 with Metal, while Open WebUI provides persistent conversations and a browser interface. Compatibility is documented, but this exact complete stack still needs its first submitted run report.
Start from a task
Use the planner to choose a model and hardware before looking for an executable path.
Open planner →Start from hardware
Find models that fit hardware you already own, then open a matching recipe.
Open hardware fit →