Liquid AI reveals 8B-A1B MoE trained on 38T

(liquid.ai)

84 points | by simjnd 4 hours ago

9 comments

  • SubiculumCode 45 minutes ago
    Anybody use their localcowork [1] before? That is where the demo lives. Or not?

    [1] https://github.com/Liquid4All/cookbook/tree/main/examples/lo...

  • chabes 1 hour ago
    The small models are getting really impressive.

    I recently realized that Qwen3.5:4B is way more capable than I thought a model that size could be.

    Combine that with the work Liquid puts into RL and fine tuning, and you get models that perform extremely well on minimal hardware.

    Combine that with your own fine tuning, and you get a specialized tool that is fast, private, and doesn’t require internet connection.

    • r0b05 55 minutes ago
      What did you use qwen3.5 4b for?
  • adityashankar 1 hour ago
    This is super interesting, I'm particularly excited for this one as it may allow teams to scale this architecture for VLAs (vision language action models), and having sparser models means more real-time actions on a locally hosted model

    demo link for anyone that wants to try this out https://playground.liquid.ai/chat?model=cmppnbgse000004l4bc8...

  • bee_rider 1 hour ago
    They seem… much better than all the models they compared against? What’s the catch?
    • FuckButtons 34 minutes ago
      They only showed the benchmarks where they outperformed?
  • mlmonkey 1 hour ago
    Question: I have a dirty car and the car wash is just 50 meters away. Should I walk or drive to the carwash?

    Answer: . . . . So, unless you have a compelling reason not to, walk to the car wash.

    • nine_k 29 minutes ago
      You did not express any desire to wash the car. After nudging, it's funnier:

      > Is my desire to make my car clean related to a car wash in any way? To driving to it?

      > Your desire to have a clean car isn’t tied to the existence or use of a car wash or to traveling to one. It stems from how much you value the effort, time, and resources you’re willing to invest in achieving cleanliness — whether that means doing it yourself, paying for a professional service, or simply enjoying the routine of a quick walk‑out. Driving to a nearby wash is just one possible method among many; the decision ultimately depends on factors such as how much time you have, how much you’d like to spend, the quality of the wash, and any personal preferences you have for hands‑on versus outsourced cleaning. In this case, walking is the simplest and fastest way, but it isn’t required for you to achieve a clean car.

      Common sense is clearly there, but we should not underestimate the colossal heap of tacit assumptions that drive "obvious" decisions in our daily life.

    • cwnyth 48 minutes ago
      I'm surprised these models haven't picked this up yet in the training data. Both Claude and ChatGPT missed that one when I posed the question to them last year.
      • tingletech 22 minutes ago
        Why would a model know that one washes cars at a car wash? We don't clean our bodies at the body wash or clean the kitchen at the kitchen wash.
        • jjtheblunt 0 minutes ago
          to your point, when my Aussie friends first mentioned a "car park" to my north american born self, i wondered _momentarily_ what that was, then realized it's sort of a fun view of what we would call a parking lot.
        • shepardrtc 5 minutes ago
          There's meaning in the term "car wash" that it understands. But I don't suspect anyone has taught it that for 99.9% of people, going to car wash ONLY means that you're going to wash your car and that it should make that implicit assumption.

          What if you're the car wash owner? Or a maintenance technician? Pretty easy to just walk over there if you're just 50ft away.

    • dominotw 23 minutes ago
      doesnt seem unreasonable.
  • HenryMulligan 1 hour ago
    Why does this not have (day-one) support for Ollama? The previous model is on there? Is it related to the ongoing refactor work or are people abandoning Ollama for other LLM engines?
    • TobTobXX 1 hour ago
      Ollama is just llama.cpp but with their own interface ontop. Liquid does support llama.cpp, but Ollama is slow in updating its llama.cpp dependency.
    • garo-pro 1 hour ago
      It does, ollama pull maternion/lfm2.5
  • ramshanker 1 hour ago
    Guess we can run this even on CPU!
  • elorant 1 hour ago
    Wow, this is fucking phenomenal. I fed it a long transcript asking it to create a summary and it executed it extremely well. For an 8B model this is quite impressive.
    • SubiculumCode 27 minutes ago
      I gave it a 2000 line python code that does some fairly sophisticated geodesic calculations on surfaces, and asked to review the code. I then asked Claude and ChatGPT to "assess the accuracy of this review" and they did not hold back. That said, its a very small model, and very fast.
  • gmuslera 1 hour ago
    Homeopathic AI