TradeMAV launches $109 RAMDeck hub on Indiegogo
The low-power hub pools memory from Windows PCs, Macs, Linux machines and Android phones to run larger AI models, with fixed funding closing November 8, 2026.
TradeMAV has launched an Indiegogo crowdfunding campaign for RAMDeck, a hub priced at $109 for early backers that links Windows PCs, Macs, Linux machines and Android phones into a single memory pool for running AI models, according to techradar.com. The campaign uses fixed funding against a $10,000 goal and closes on November 8, 2026.
On each contributing device, a node agent starts llama.cpp's ggml RPC server, and any compatible coordinator can drive it over the standard llama.cpp RPC protocol. TradeMAV's own software adds automatic discovery, layer placement that fills GPUs before system RAM, failure recovery, a dashboard and an OpenAI-compatible API.
The company's published benchmarks report 39 tokens per second for Qwen3-Coder 30B across a Beelink mini PC with an RTX 3060 and an M4 Mac mini, and 16 tokens per second for a 40B REAP variant of Qwen3-Coder-Next. A 7B model reached 43 tokens per second in testing.
None of TradeMAV's published pages list RAMDeck's processor, memory, ports or power draw.
Memory prices behind the pitch
TradeMAV claims a 64GB DDR5 kit went from about $191 in August 2025 to $1,118 a year later. Retail data from 3DCenter put DDR5 at 486% of its July 2025 price by mid-August 2026, and Samsung has told analysts the memory shortage will persist through 2028, while SK Group's chairman warned it could run until 2030.
Pooling software is not new to the category: Exo Labs' open source exo has offered automatic device discovery and a drop-in API across computers, phones and single-board computers since at least early 2025.
Quick answers
How much does RAMDeck cost?
Early backers can get RAMDeck for $109 through the Indiegogo campaign.
When does the RAMDeck Indiegogo campaign end?
The campaign uses fixed funding against a $10,000 goal and closes on November 8, 2026.
Which devices can RAMDeck pool memory from?
Windows PCs, Macs, Linux machines and Android phones.