[drnick1]

How useful is the second 3090 in this setup? I run the 5-bit quantized model on a single 3090. Does the second 3090 allow you to use the full precision model instead or a less aggressive quantization by splitting the layers? What about running the 35B model instead?

[tedivm]

More memory means less aggressive quantization, more concurrent requests, and larger context windows. I also get a boost in tokens per second (not double, about 1.5x compared to a single GPU).

The 35B model is an MoE (mixture of experts), which uses only a subset of parameters at a time. The 27b one is slower but has way better performance.

[drnick1]

Nice, I wish I could find another cheap 3090 somewhere.