Author of llama.cpp's k-quants and SOTA low-bit quantization
Quantization researcher · current
Iwan invented the k-quant family that nearly every GGUF model on every Mac uses, then pushed on to state-of-the-art 2-bit quants with the perplexity tables to prove them. His rigor is why a 70B model fits in a MacBook's memory without falling apart.
We built this from your public work because we think it deserves celebrating. You did not ask us to, so the only fair thing is that you decide what happens to it. Claim it and it is yours to edit. Ask us to change something and we will. Ask us to take it down and it is gone within 72 hours — free, no account needed, and nobody will try to talk you out of it.