Ollama maintainer for GPU discovery and backends
Public work celebrated here · current
Daniel does the hard hardware-enablement work in Ollama, teaching it to find and use whatever GPU a machine has, and drafting the MLX backend path for Macs. Making models actually reach the silicon is exactly the craft this directory exists to thank.
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.