|
|
|
|
|
|
by pants2
3 days ago
|
|
|
With a tps and a token price you can calculate approx. price per hour of running the model! $2.61/M tokens * 1,000 tok/s = $9.40/hr That would be pretty cheap for an 8-GPU node which would typically run around $45/hr or more. Guess this depends on how many parallel streams it can handle. |
|
|