Comment Comment by riknos314 Great question. Nobody knows.The cool thing about models designed for cheaper inference is that post-training (which often requires inference as a part of the feedback loop) becomes cheaper as well, so almost certainly cheaper than models that are less optimized. parent riknos314 6 days ago
The cool thing about models designed for cheaper inference is that post-training (which often requires inference as a part of the feedback loop) becomes cheaper as well, so almost certainly cheaper than models that are less optimized.