FitLLM – open-source calculator: will this LLM fit my GPU/Mac? (accurate on Gemma 4 / Qwen 3.6)

Live: https://fitllm.run Engine (MIT, one file): GitHub - click6067-ship-it/fitllm-engine: Accurate LLM memory & speed calculator — models sliding-window/linear/MoE attention where naive VRAM/RAM calculators are 4–11× off. Apple Silicon + NVIDIA RTX · GGUF · one MIT file. Powers fitllm.run. · GitHub Most calculators use the textbook KV-cache formula and are multiples off on modern models: Gemma 4 (sliding-window), Qwen 3.6 (linear attention), MoE. FitLLM reads each model’s config.json and models each layer type separately. Apple Silicon + NVIDIA RTX. Paste any HF model id. Estimator, not ground truth.