Tell us your hardware budget and what you want to make. We pick a consistent, working stack from our catalogue — workflow engine, model, runner, training tools. Empty slots tell you why nothing fits, instead of pretending.
Run language models on your own hardware — Ollama, llama.cpp, LM Studio. Cards in this tier: RTX 4070 Ti SUPER, RTX 4080, M-series 16 GB.
One-command local LLM runtime.
Role: The runtime that loads quantised LLMs and serves them locally.
ALT // Open WebUI — self-hosted chatgpt-style frontend for ollama / openai.
The reference open-source speech-to-text model.
Role: For when you outgrow a single GPU and need to serve workloads.
ALT // CrewAI — role-playing agents working as a crew.
Every pick is a function of three things in our catalogue: minimum VRAM (must fit your budget), power-user score (60% of the weight), and trending score (20%). We add small bonuses for open-source licensing and beginner-friendly setup. No paid placements, no “sponsored” tier — if it's not in our catalogue, it can't appear here.
