No vision support?
Liquid AI reveals 8B-A1B MoE trained on 38T
31–40 of 101 posts
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#32Earlier quoted context omitted.
doesnt seem unreasonable.
These faux questions always have a valid interpretation that the asker doesn't admit (for some reason). The model is then castigated for not making an opinionated choice
That’s not what’s happening.
The question is revealing that the model has a model of language but not of reality. It knows what words go together, but not real-world concepts.
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#33Liquid does amazing work, but I kinda feel like they are overtraining their models. 38T tokens seems like a lot for an 8B model
What's the downside? Don't they stop when they hit diminishing returns?
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#34Question: 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.
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 you…
Reminder that the human baseline for the car wash question is also pretty bad.
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#35They seem… much better than all the models they compared against? What’s the catch?
It's twice the size?
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#36Hmm, I asked it who made it, and it says Google?
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#37I really love how fast it is! Their press release comparing it on Strix Halo and M5 Max are impressive. It going twice as fast at GPU benchmarks even more so!
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#38The 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.
What did you use qwen3.5 4b for?
I use it for triaging my messages and emails and reminding me how all of it ties together. It uses Obsidian to know where to put stuff and how to connect information. It isn't perfect. It's very slow (using a 32GB M2 Max) but fast enough for my needs.
A good example of how it's helpful is that it will make certain things relatively frictionless. Like, I need to pay property taxes. I hate this stuff. I got the email reminder from my municipality and it made an entry in my TODOs which points to page with instructions to pay the taxes, including my folio and access numbers for when I log in. That was taken from the email and a document which contains past property tax information. I have it all there, but it compiles relevant data into dedicated TODO pages.
I'm so bad at doing all of this myself. I really don't enjoy it. Send me to buy a carrot at the store and I'll happily walk 30 minutes there and back to do it. It isn't the effort so to speak; it's how unrewarding, inefficient, and bureaucratic it all is. I'm allergic to it. Why isn't it baked into my income taxes? Why are we still doing this?
Sometimes it does a really bad job of making TODOs. Like my wife messaged me about what our dinner plan was, so Qwen went ahead and made a plan for chicken meatball soup based on messages from a week earlier. It totally fabricated the recipe. Yet, I don't know, it was still helpful to be reminded that I'm in charge of dinner.
It's probably best at scaffolding responses to emails I don't want to send. I will write it, but I appreciate basic information being fleshed out so I can write it without jumping around looking for files or numbers or whatever constantly.
I use it with a custom harness. It could be a lot better. Everything about it could be better. The model is remarkably good for its size and price, though.
Letting Sonnet 4.6 do it instead always yields much better results, much faster, but it's kind of like using a new phone vs a super old one. They can both get you there. The sound quality and camera might be worse, it doesn't look as fancy, but the new one is $1200 and the old one is free on marketplace if you're handy with a screwdriver and a fresh battery. Sounds great to me
Worth noting: this was all vibe-coded using Opus 4.6 and 4.7. It's the only project I've built that is strictly vibe-coded. It's simultaneously exciting and disgusting. I'm not sure if I'll ever 'software engineer' it, or I'll just let it be slop. It works.
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#39Question: 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.
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.
ChatGPT still says walk but adds:
>The main reasons to drive such a short distance would be if you're bringing the car specifically to be washed, carrying something heavy, or the weather or walking conditions make it impractical.
>If your goal is to get your car washed, you'll need the car there—so driving makes sense. If you're just going to talk to someone at the car wash or check it out, walking is probably faster.
Re: Liquid AI reveals 8B-A1B MoE trained on 38T
#40I just tested this on a bug fixing benchmark I'm working on.
It did not perform as well as I expected. Qwen2.5-Coder-3B (2 years old) outperformed it by a wide range -> fixing ~50% of bugs whereas this model only fixed ~12%.
Granted, it's not a coder specific model, but given its benchmark performance to Gemma models, and that it's two years newer, and that it's an MoE with 8B total params, I expected it to be more competitive.