Hacker News new | ask | show | jobs
by jychang 99 days ago
No, Opus cannot be 10x larger than the chinese models.

If Opus was 10x larger than the chinese models, then Google Vertex/Amazon Bedrock would serve it 10x slower than Deepseek/Kimi/etc.

That's not the case. They're in the same order of magnitude of speed.
3 comments
Filligree 99 days ago
They serve it about 2x slower. So it must have about 2x the active parameters.

It could still be 10x larger overall, though that would not make it 10x more expensive.

link
jychang 98 days ago
Yes, but I highly doubt they would increase sparsity much vs the chinese models.

That's how you get Llama 4.

Pretty much every major lab settled on ~3-5% sparsity for a reason.

link
bakugo 99 days ago
I agree that Opus almost definitely isn't anywhere near that big, but AWS throughput might not be a great way to measure model size.

According to OpenRouter, AWS serves the latest Opus and Sonnet at roughly the same speed. It's likely that they simply allocate hardware differently per model.

link
jychang 98 days ago
The numbers look about right. Opus 4.5 is about 1.5x the size of Sonnet 4.6, and Opus 4/4.1 is about 5x the size of Sonnet 4.5/4.6.

Note that Opus 4.5 is about 1/3 the size of Opus 4/4.1 (and 1/3 the price in the API)

link
torginus 99 days ago
My understanding is that for MoE with top K architecture, model size doesn't really matter, as you can have 10 32GB experts or a thousand, if only 2-3 of them are active at the same time, your inference workload will be identical, only your hard drive traffic will incread.

Which seems to be the case, seeing how hungry the industry lately has been for hard drives.

link