The letter

One letter a week, in your inbox.

The signal of the week, what shipped, what to try, and the editor's note. No tracking, no ads, nothing else.

We keep your address, your language and the date you joined, nothing else. Every letter has a one-click unsubscribe link that deletes the record.

← Accept All   Archive
NVIDIA Technical BlogSilicon

Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each

September 15
Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each

How can a 30B-parameter model activate only 3B parameters per token, and still use the capacity of the larger model? Nemotron 3.5 Lightning illustrates the... How can a 30B-parameter model activate only 3B parameters per

Models & releasesAgentic AI / Generative AIData Center / CloudAI InferenceLLMs
Read at NVIDIA Technical Blog ↗

Related

More from NVIDIA Technical Blog on Accept All.