zlacker

[parent] [thread] 3 comments
1. s17n+(OP)[view] [source] 2022-05-24 00:57:57
Running inference on one of these models takes like a GPU minute, so they can't just let the public use them.
replies(2): >>throwa+31 >>yeldar+b6
2. throwa+31[view] [source] 2022-05-24 01:06:50
>>s17n+(OP)
They can absolutely do for it if they charge the public the cost of GPU time.
3. yeldar+b6[view] [source] 2022-05-24 01:52:52
>>s17n+(OP)
Can't be this; Google Colab gives out tons of free GPU usage.
replies(1): >>astran+as
◧◩
4. astran+as[view] [source] [discussion] 2022-05-24 06:02:57
>>yeldar+b6
Google has a lot of GPUs, but even so Colab seems like it’s a lot cheaper than it should be. You can get some very good GPUs on the paid plan.
[go to top]