Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU. Parent comment
In general systems usually have PCIE version with bandwidth better than RAM of that system.
For example a system with DDR4 (27Gbs) usually has at least PCIE4 (32Gbs at 16x).
But you can bottleneck that by building a DDR5 (40Gbs) system with PCIE4 card.
There are no comments on this comment yet.
In general systems usually have PCIE version with bandwidth better than RAM of that system.
For example a system with DDR4 (27Gbs) usually has at least PCIE4 (32Gbs at 16x).
But you can bottleneck that by building a DDR5 (40Gbs) system with PCIE4 card.