The right model depends on the task.
2.7M followers
97,320 views
33 Comments
Comments from the original post on X (Twitter)

@nvidia
Learn more:
37 likes

@liangsays
@MTSlive so awesome to have kari on the show!
5 likes

@denys_khomyn
@ChrisJBakke @MTSlive NVIDIA monitoring the situation 🤘
4 likes

@DataVLTAI
@MTSlive The smarter the routing, the more important the data behind each decision becomes. Model choice is only one part of the stack.
2 likes

@pixelsilicon
@MTSlive Model routing by task is becoming essential once agent workflows get multi step. One model for everything is rarely optimal on cost or latency.
1 like

@KVCacheStore
@MTSlive I'm a contributor to Switchyard. If anyone wants help setting it up let me know.
1 like

@Joelramirez1968
@MTSlive ⚓️✅❌🚀🎇
1 like

@glitchtruth
@MTSlive Doesn't matter which model wins the routing fight, every single path still ends at an Nvidia GPU.
1 like

@OGNVDASOL
@MTSlive @elonmusk
1 like

@ZeeBside
@MTSlive oxi, now proibida no mundo todo

@pusulainfra
@MTSlive model routing based on latency + cost is the part most teams still underestimate

@cameron_h23
@MTSlive Model routing is becoming core infrastructure for agent systems—use the expensive reasoning model where it matters, optimize everything else around it.

@aiseomastery
@MTSlive Smart routing saves real money

@robertahero
@MTSlive The right model depends on the task.

@marissarobinart
@MTSlive 👍

@JWPAX3051
@MTSlive Love how NeMo Switchyard lets us pick the perfect model for each step—smart, flexible, and cost‑savvy!

@mixtureofmodels
@MTSlive

@SpendLensAI
@MTSlive Routing only works after teams save representative workflows and set a quality floor.

@coderchrisdean
@MTSlive Per-step routing is right, and it only works if you have per-step evals: without them you're routing on vibes and the cheap model quietly tanks one node of the workflow.

@nockrail
@MTSlive rubin vs tpu pileup this month is the whole story. everyone shipping silicon at once.












