It’s always a little strange to see people link the Hyprland toxicity post when so much of it wasn’t fact-checked by the author or was presented without the context to make it look worse.

They use Bing to power the web search tools the model has access to.

Source:

ChatGPT searches based on prompts and may share disassociated search queries with the Bing search engine to return web results.

deleted by creator

Its trained at native MXFP4 with MXFP8 activations layer, so you need around 1.5TB of VRAM to fully offload it without taking into account the context cache. It might be doable to do some smart expert offloading and swapping, but expect minimum 500GB of VRAM and 1TB of system RAM minimum and the t/s would be reduced.

Its only realistically runnable on datacenter grade gpu at decent speed for now (and judging from the price of ram for the next few years)