- Thunderbolt 5 bandwidth brings external GPU hardware closer to workstation territory
- Local AI inference gains attention as cloud costs continue to rise
- Developers are increasingly exploring running language models directly on personal hardware.
External GPU cases have been around for some time, typically associated with laptops for gaming and graphics acceleration tasks that exceed the capabilities of mobile processors.
Plugable’s recently released TBT5-AI falls into this category, but features a design focused on connecting desktop graphics hardware to laptops for on-premises AI workloads.
The case provides a full-length PCIe x16 slot that allows users to install a desktop graphics card inside the external chassis.
Article continues below.
Desktop hardware in an external cabinet
An integrated 850-watt power supply provides the power needed to run high-performance GPUs that would normally only run within desktop workstations.
For connectivity, this device comes with a single Thunderbolt 5 cable, which allows direct connection to a laptop and supports up to 80Gbps of bi-directional bandwidth, while a boost mode can increase performance to 120Gbps for certain workloads.
Inside the case, this bandwidth links the installed GPU via PCIe 4.0 x4 lanes, reducing transfer bottlenecks that limited previous external GPU designs.
In addition to housing the graphics card, the system functions as a hub that expands the connectivity of the connected laptop.
It offers up to 96 watts of charging power while also providing 2.5 gigabit Ethernet networking and multiple high-speed USB ports.
According to Plugable, many engineers increasingly want to keep model processing and data handling within their own systems, and the TBT5-AI offers just that, as it is designed for developers experimenting with local AI inference environments.
The device allows developers to run large language models directly on local hardware instead of sending workloads to cloud infrastructure.
It supports common local AI frameworks, including llama.cpp, Hugging Face models, and Nvidia’s NIM inference platform.
Plugable Chief Technology Officer Bernie Thompson said the hardware is aimed at industries where protecting sensitive information remains a strict operational requirement.
“Data privacy is not a feature but a mandate,” Thompson said, referring to sectors such as healthcare, financial services and legal organizations.
Plugable is also preparing enterprise versions called TBT5-AI16, TBT5-AI32 and TBT5-AI96 that will include included graphics processors.
These configurations will integrate a software environment called Plugable Chat, described as an isolated AI orchestration platform for regulated organizations.
The company claims that these systems will move AI processing from subscription-based cloud services to a locally controlled computing infrastructure.
Priced at $599.95 as a standalone unit, the Plugable TBT5-AI enclosure was officially released a few days ago and is now available through Amazon and Plugable.com.
Via Macsources
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
