|
|
|
|
|
|
by tedivm
28 days ago
|
|
|
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. |
|
|