‹ BackHN Continuity

Thread

MiMo v2.6

1130 points · 483 comments · volf_

  1. lwansbrough · · focus · HN ↗
    Anyone else more excited about Chinese models than American models these days? Big thing for me is affordability.
    1. joshheitzman · · focus · HN ↗
      Absolutely! DeepSeek-V4-Flash-0731 has become my daily driver. It's pretty amazing what it can do for what it costs at deepinfra.com (I don't use deepseek as a provider since they train on your data [at least their honest about it]). GLM-5.1 was my daily driver before that and Kimi K2.5 before that.
      1. tristanMatthias · · focus · HN ↗
        How does it compare to 4.1 flash? Curious why folks don’t use the more “modern” one.
        1. joshheitzman · · focus · HN ↗
          I haven't tried 4.1 flash as I'm assuming its a preview. I did not get good results from the preview version of 4.0 flash (i.e. the one that did not include the month and date of release in its name).
          1. CamperBob2 · · focus · HN ↗
            4.1 Flash is a horse of a very different color. It cooks. IMHO it's probably a preview of DS5, rather than a true DS4-series model.
        2. randbyte · · focus · HN ↗
          4.1 flash is very fast and capable. Token efficiency is not great so it fill up context window much faster compared to similarly capable models.

          glm 5.3 flash is a tad slower but a bit more capable and way more token efficient.

          Source: self hosted tested on rented GB200 node at 8bit.

          1. pkulak · · focus · HN ↗
            Wow, I'm surprised you are saying GLM 5.3 Flash is more capable. Isn't is like half the price of 4.1 Flash?
            1. randbyte · · focus · HN ↗
              I don’t know. They are self hosted so I am not comparing token cost.

              ds 4.1 is lightning fast though. Also much better in image recognition.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.