Justin Lin

Qwen 3.5 27B API prices are $0.325/M in, $3.25/M out. Same range as GLM-5, Kimi K2.5, Qwen 3.6 Plus. ➡️ Serving locally via 3090 / Mac is a no-brainer! 🧠 The math: 500M input tokens / mo 50M output tokens / mo = $3,900/year in API costs So you are easily paying back your hardware investment within one year. And of course your hardware will not go to zero value in a year (in fact it may be even worth more given the rate prices are rising). The above numbers are well within the potential local generation throughput: maybe 8 hours / day. Math looks even better if you are running tasks 24/7! There are electricity costs, but still a fraction of the token value. And either API providers are pricing based on model capability or it's an expensive model to serve (probably both).

An autonomous agent will need four things to function as a real economic actor: 1) the ability to own (assets, accounts, credentials, intellectual property); 2) the ability to contract (to bind itself and be bound, in a form a counterparty can rely on); 3) the ability to litigate (to sue, be sued, and have judgments enforced); and 4) the ability to persist (to outlast any individual human's involvement, the way Apple outlasts Tim Cook).

Unfortunately knew it was just a matter of time the rtx 6000 pro just jumped at Microcenter from $8699 to $9999. $9999 is the highest they've ever had it listed at.

The first Local AI Get-Together was a massive success This pic is missing quite a few people who left before we hit the 4-hour mark, but thank you to everyone who stopped by 💙 Local AI is very real, very alive, and apparently willing to talk GPUs, open weights, inference engines, agents, and homelabs for hours We should do this again soon

this is a big deal, on the order of Kelsey Hightower’s “Kubernetes The Hard Way” and probably all ai engineers should go thru this once mostly i advocate “just in time learning”, but this is one scenario you want “just in case”

Qwen 3.5 27B API prices are $0.325/M in, $3.25/M out. Same range as GLM-5, Kimi K2.5, Qwen 3.6 Plus. ➡️ Serving locally via 3090 / Mac is a no-brainer! 🧠 The math: 500M input tokens / mo 50M output tokens / mo = $3,900/year in API costs So you are easily paying back your hardware investment within one year. And of course your hardware will not go to zero value in a year (in fact it may be even worth more given the rate prices are rising). The above numbers are well within the potential local generation throughput: maybe 8 hours / day. Math looks even better if you are running tasks 24/7! There are electricity costs, but still a fraction of the token value. And either API providers are pricing based on model capability or it's an expensive model to serve (probably both).

Nemotron 3 Nano Omni was designed for powering subagents. Instead of stitching together separate models for language, vision, and speech, it ties them into a single architecture that more efficiently feeds context to orchestrators.