ZH version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
60% Positive
Analyzed from 159 words in the discussion.
Trending Topics
#main#workstation#pci#models#halo#personal#station#https#com#looks

Discussion (5 Comments)Read Original on HackerNews
Theres a few potential “problems” I see with it - main system RAM is about 30-40x slower than that of the GPU’s and you will have PCI-e as a bottleneck getting working data to or between the GPUs.
In practice is the 400-500GB/s main memory limiting some use cases, or is the PCI-E bus the main issue with these types of systems?
That all said, running frontier models locally offline would be very nice
Each MI350P[1] in the TR Halo Station has 144GB VRAM and with 4.6 PFLOPs peak MXFP6 performance.
Four liquid cooled? Yes please.
[0] https://a16z.com/building-a16zs-personal-ai-workstation-with...
[1] https://www.amd.com/en/products/accelerators/instinct/mi350/...