So many conferences are mid. Why was BSC 2025 so good?bgthompson.codeberg.page1 points·by probablydan·قبل 11 شهرًا·0 comments
probablydan·قبل 11 شهرًا·discussCan these be used for local inference on large models? I'm assuming the 128G of memory is like system memory, not like GPU VRAM.