TradeMAV’s $109 RAMDeck Hub Crowdfunds Multi-Device AI Inference
TradeMAV is crowdfunding RAMDeck on Indiegogo for $109, offering a low-power hub that coordinates model inference across Windows PCs, Macs, Linux systems and Android phones. It divides model layers among devices rather than merging their RAM at the hardware level, building on llama.cpp’s free RPC backend and adding device discovery, layer placement, failure recovery, a dashboard and an OpenAI-compatible API. Vendor demonstrations showed fast MoE results but much slower dense-model performance of around two tokens per second, while the hub’s processor, memory, ports and power draw remain undisclosed.
RAMDeck packages a free distributed-inference mechanism into a crowdfunded convenience product, but undisclosed specifications and vendor-reported speed trade-offs make clear how it differs from DIY llama.cpp and exo setups.
- TradeMAV's RAMDeck hub is crowdfunding on Indiegogo, listed at $109 for early backers
- The engine underneath is llama.cpp's RPC backend, which anyone can already run at no cost
- Its fastest demos lean on an RTX 3060 and mixture-of-experts models, while denser models manage around two tokens per second
With DDR5 now costing roughly five times what it did in mid-2025, a small company called TradeMAV thinks the answer to running bigger AI models at home isn't buying more RAM, but borrowing the memory already sitting in your other devices.
The argument, which is hard to rule against, is being pitched in the form of RAMDeck, which TradeMAV is crowdfunding on Indiegogo, a small, low-power hub that links Windows PCs, Macs, Linux machines and Android phones on a home network into one memory pool, so a model too large for any single device can be split across all of them.
The campaign uses fixed funding against a $10,000 goal and closes on November 8 2026, 2026, according to the company's launch video, while a cost comparison table in TradeMAV's own RAM pooling guide lists the hub at $109 as an early-bird reward.