HHCJ6 Dell NVIDIA Tesla K80 24GB GDDR5 PCI-E 3.0 Server GPU Accelerator (Renewed)

Sadly I bought this card and then left it on a shelf for nearly 7 months as I was too busy to get the cooling set up for it. When I finally installed it, it not only failed to fire up but it also prevented my PC from booting - basically several hundred pounds of brick. With the time that elapsed between purchase and finding out it was worthless there wasn't much I could do - can I prove it broke itself whilst sitting in a box on the shelf? Of course not - would never touch a refurbished Amazon product again.

I am often amazed at the ignorance of some people, this is not a card for graphics. but people purchase it anyway . Thinking they are getting a cheap graphics card and then complain that it doesn't have any graphics. Anybody who's purchasing it for such an application is just deluding themselves. Having said that. What the card Is good for is providing your system with a processing subsystem for applications such as running LLM's for which it works extremely well.. If you do have it in a graphics-based system and you wanted to offload some Cuda functions to it . It may and I say may be possible. But probably slower than running on your native graphics card. Yes it runs hot because it's supposed to . It's a passive cooling system and requires a tremendous amount of airflow like you would find in a server. There are a number of fan adapters for this card , and one could make, if one were industrious enough a liquid cooling or Peltier cooling solution. this card works for exactly the reason I purchased it , which is being able to load LLM's I use a combination of backend applications such as a ollama coupled with WebUI and for TTS I'm using Coqui-TTS. All of this pairs with Wingman AI for the front end interface. I can run some fairly large models up to 27B on one card in conjunction with my main 4090 graphics card I can run 30 and 32B these are fairly large and accurate models.

Una gráfica espectacular para Machine Learning pero, por desgracia, los drivers de la K80 son incompatibles con los de mi otra gráfica, una Nvidia Titan X Pascal de 12Gb. ¡Una verdadera pena!

una porqueria, echa fuego y no va

Had to redo the thermal paste on the GPU (suggest you do the same if you get one) also suggest getting fans for it as it’s built with passive cooling which is no bueno… the active cooling systems are easily found and run about $30 bucks… a bit loud but well worth it. The gpu is good for LLM local builds and some other large tasks. It functions fine and for the price I will pick three of these any day over a new 5080. Not as fast as the Nvidia Instinct but more applicable use…

It works great in ANSYS, but it runs SUPER hot like I'm not even kidding. I have 2 stacked 140mm fans blowing at it through a fan shroud and it's idling at 54 and 87 degrees on the 2 cores. Loaded it up to 100% and it shot up to 95C within 30 seconds, though it finished the analysis within that time so no complaints. If you are running this in a desktop, you better water cool it. A couple of little "features" I'm running an 8700k on Asus Maximus Hero X with 2*Strix GTX1080 already installed. This card goes through PCH and does not take up any PCIe lanes, did not have any impact on SLI performance. There is also no performance hit on my 970Evo M.2 SSD which is also going through the PCH. When it overheats and crashes, it doesn't bring the whole system down. It just freezes for a second but your computer can keep running just fine.