‹ BackHN Continuity

Thread

Ember-1

589 points · 249 comments · gmays

  1. soerxpso · · focus · HN ↗
    I don't see why I would be interested in this model, considering the price difference. They advertise that it's the same as Kimi K3 in half the tokens. But the pricing is double the pricing of K3. So why do I care if it uses fewer tokens, if I'm paying double per token?
    1. bigmadshoe · · focus · HN ↗
      Because you care about how many tokens are used per task. What you said is like only caring about the price of gas and not gas mileage of your car.
      1. verdverm · · focus · HN ↗
        it's not exactly the same, the model stills "weighs" the same

        here, it does less work, it's more like driving half as far but still paying the same total cost

        this being said, K3 and E1 models are priced the same at $3.00 / $0.30 / $15.00

        <a href="https:&#x2F;&#x2F;fireworks.ai&#x2F;models&#x2F;fireworks&#x2F;kimi-k3" rel="nofollow">https:&#x2F;&#x2F;fireworks.ai&#x2F;models&#x2F;fireworks&#x2F;kimi-k3

        <a href="https:&#x2F;&#x2F;fireworks.ai&#x2F;models&#x2F;fireworks&#x2F;ember-1" rel="nofollow">https:&#x2F;&#x2F;fireworks.ai&#x2F;models&#x2F;fireworks&#x2F;ember-1

        1. bigmadshoe · · focus · HN ↗
          From reading the blog post, it is essentially exactly the same as the car example. It delivers the same performance on tasks, but using 40% fewer tokens. This is the same as a car getting you to the same destination but wasting less energy on excess heat, wind resistance, or whatever else affects fuel economy (I am not an expert, obviously). I am paying for an LLM to complete tasks for me, not for the intermediate tokens.
          1. verdverm · · focus · HN ↗
            I&#x27;m with you, I wrote prior comment under the assumption that they were priced differently (from GP claim as such), but they are priced the same (on Fireworks)

            Will be taking Ember-1 for a spin on Monday and hopefully enjoy those better MPGs

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.