When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works .
That list of words usually doesn't belong in the same sentence as GPUs, so it merits close inspection. First and foremost, the WiCi One leverages the WiFi 7 protocol to transmit data to and from the card. The firm says that client machines keep a GPU driver that makes the operating system think it's a graphics card just like any other, while in reality they'll be talking to the WiCi One over the network.
However, as WiCi explains in great detail, just blindly doing that would make for a terrible eGPU, as the standard communication between host and card is extremely chatty. That's not a problem with the sub-microsecond latency of PCIe 5.0, but would quickly turn even basic status querying operations into multi-second affairs. Large computations with lots of data shuffled back and forth could hypothetically take hours.
The company claims its driver software performs a great deal of data caching, deduplication, and compression, and is also very judicious about what type of hardware requests can be handled locally versus those that really do need to go over the airwaves.
This mode of operation and its corresponding separation of concerns bring several advantages: theoretically, the one GPU could be used on multiple machines. There are Python libraries for passing the WiCi One as any other GPU to LLMs, and also a standard HTTP API for network access, once again lending credence to the fact that multiple clients could use the WiCi One without any special configuration.
Perplexity’s local AI agent comes to Windows, but only for RTX GPUs with at least 24GB of VRAM
Enthusiast turns a Lenovo Yoga laptop, an M.2 slot, and an AMD Radeon RX 7900 XT into 'the world's stupidest' desktop for local AI chatbots
Colibrì proof-of-concept gains frontier-level 1.5-TB AI model
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/pc-components/gpus/SPONSORED_LINK_URL
- https://www.tomshardware.com/pc-components/gpus/wici-one-unveils-wireless-wi-fi-7-egpu-with-built-in-4tb-ssd-for-local-ai-usd1-999-box-leverages-wifi-7-to-present-a-remote-card-as-local#main
- https://www.tomshardware.com/membership
- Memory chips are now more expensive than compute chips on a per-area basis
- AI Infra Summit: NVIDIA Vera Rubin and DSX Platform Advancements Showcase Energy Efficiencies of Optimizing Tokens Per Watt for AI Factories
- China swiped classified F-35 stealth fighter parts that were diverted through Hong Kong
- How Open Science Can Help Researchers Prepare for the Next Pandemic
- 5 Companies Using NVIDIA AI for Clean Energy
Informational only. No financial advice. Do your own research.