Hardware

RAMDeck: Pool Your RAM. Run Bigger AI.

A small plug-and-play hub that connects the computers, Macs, and phones you already own into one pooled-memory network — so you can run AI models too big for any single device, without the cloud

$13,423
Indiegogo 灵活筹资
57 支持者
0 剩余
3 回报档位
⏳ 该项目已结束众筹

项目介绍

RAMDeck turns the computers, phones and other devices you already own into a single, unified local AI cluster by pooling their RAM. A small hub acts as a conductor, directing model layers to each device so you can run large language models locally without recurring cloud fees or buying expensive new hardware. The kit includes a pre‑flashed hub, node agents for Windows/macOS/Android, an Ethernet cable, and OpenAI‑compatible API access, enabling self‑healing, dynamic context scaling and local knowledge‑base ingestion. With shipping estimated for February‑March 2027, RAMDeck offers a one‑time cost against the endless expense of cloud subscriptions.

核心亮点

▸ Pools RAM from existing devices to run massive AI models locally.
▸ Self‑healing cluster automatically recovers from node drops and network hiccups.
▸ Includes OpenAI‑compatible API, knowledge‑base ingestion and local model training.

技术规格

规格详情
Power Adapter5V/4A (US only)
Ethernet CableIncluded
Supported OSWindows, macOS, Android
API CompatibilityOpenAI‑compatible (/v1/chat/completions)
Shipping EstimateFebruary – March 2027
Retail Price$199
Source AvailabilityGitHub (Apache 2.0 with Commons Clause)
Dynamic Context ScalingUp to 32,000+ tokens with pooled RAM

回报档位

位支持者
Super Early Bird
USD109
~$109 USD
RAMDeck Hub, pre‑flashed and ready to go, plus node agent installers for Windows, macOS and Android contributor app. Everything you need to start pooling RAM today.
位支持者
Early Bird
USD139
~$139 USD
Same RAMDeck Hub and full node agent access, available after the Super Early Bird tier sells out.
位支持者
Indiegogo Special
USD159
~$159 USD
Standard campaign pricing once both early tiers are gone; still well below the retail price of $199.

风险与挑战

Performance depends on network stability; Wi‑Fi drops or sleeping nodes can interrupt inference and require model reloads, which take minutes for large models. Wired Ethernet and keeping devices awake are recommended to minimize disruptions.

项目洞察

50
TopNice 评分
$235
平均认捐
Oct 13
追踪起始
134%
已达成
📝
项目更新

开发进度、发货时间线和公告

查看所有更新 ↗