Hi everyone, I'm new here - because I only have a laptop and I only just realized local models are actually good enough now. So I'd like to share my experience, in case it helps others, and also to learn from the more experienced people here. This is the first model that works for me on my ASUS Zenbook Pro 14 (RTX 4060 8GB VRAM, 64GB RAM): fast enough: ~27TPS generation speed at 32k context, or ~18TPS at 256k context smart enough: it can read and write files, use skills, execute CLI com...