This crowdfunded $109 hub wants to pool the RAM in your old PCs, Macs, and phones to run bigger AI models — but the engine underneath is software you can already get for free
Can't stomach DDR5 at five times last year's price? RAMDeck wants to borrow your other devices' memory instead, and it admits that won't be fast.
TradeMAV's RAMDeck hub, aimed at pooling memory from old PCs, Macs, and phones to run larger AI models, is raising funds on Indiegogo for $109. The hub operates using llama.cpp's RPC backend, which can be run for free. Its performance varies, with dense models achieving around two tokens per second and a 7B model reaching 43 tokens per second.
RAMDeck's main advantage is its ability to connect various devices, including Windows PCs, Macs, Linux machines, and Android phones, into a single memory pool. However, the hub's specifications and performance are not well-documented. Some users may find llama.cpp's free software and open-source alternatives more suitable for their needs.
Written by urgent.news from TechRadar's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.