will this 14B model fit in my VRAM? why is this running at 3 tokens/sec? Built a CLI to stop asking these questions. 𝗟𝗟𝗠 𝗖𝗵𝗲𝗰𝗸𝗲𝗿 scans your GPU/CPU and scores 6,900+ @ollama models. Tells you what runs best on YOUR machine. npm install -g ollama-checker