zlacker

[parent] [thread] 1 comments
1. storys+(OP)[view] [source] 2026-01-28 12:24:54
I thought the RTX 6000 Ada was 48GB? If you have 96GB available that implies a dual setup, so you must be relying on tensor parallelism to shard the model weights across the pair.
replies(1): >>embedd+d2
2. embedd+d2[view] [source] 2026-01-28 12:40:08
>>storys+(OP)
RTX Pro 6000 - 96GB VRAM - Single card
[go to top]