Qwable 5 27B: New FREE + Local + Open Source!

So today I'm going to be showing you Quable 27B Coder, which is a new coding local model. And I'm going to show you exactly how it works. Now, we actually built some interesting stuff with this, far more than what we usually create with local models. So that impressed me in the first place. Here's for example, a landing page that we created locally using Qwable. And it was pretty easy and simple to create. It moves in the background. It looks better than 99% of those local websites that you usually create. I wouldn't say it's anywhere near Frontier level, but at the same time, it can create some pretty cool stuff better than some of the things that I've built with other models. And I'll show you some example comparisons in a second as well. And we'll look at how it compares versus other local models that I've tested recently, like for example, or NIF or Qwifos. And I do think these local models are getting better and better. And this is one of the best ones I've seen recently. So this is a cool little game we've built out. Here's another one. The thing that I will say here is that if you look at this, it kind of feels like last year's Frontier, if that makes sense. So it's not like going to start competing with Opus 4.8 or Fable 5 tomorrow, but it can build some pretty cool stuff. And this is actually better than I expected it to be when it comes to building out with these local models. So how does this work? Well, essentially what we built here is Quable 5.27B Coda. It's open source. It's free to run. And it just dropped on Hugging Face. Pretty good so far. Just got updated end of June. And it's got a Quen 3.6 27b base. So that is the base for creating this. So it's free to use, free to use locally. And we actually ran it with Apple MLX, which is a free open source set up just for using local models so we can run LLMs from Hugging Face using the system. And that's how we ran it. You can't get it through OLAMA. And if you're wondering how it performed on the benchmarks here, yeah, it did pretty good, right? I would say in terms of local models, as far as they go, it's right at the top of the leaderboard from everything we've tested out recently. So, for example, recently we've tested out Gemma 412b, Quifos 9b, or NIF 1.0. And I would genuinely say like the quality of stuff that we got from our NIF is nowhere near the same level as the quality of stuff we got from Quable. Loving these names, by the way. So it's actually my favorite local model so far. I'm on a Mac Studio, Apple M4 Max, 36 gigabytes of memory. When I actually run and create stuff with this model, I can definitely feel like the whole setup runs a bit slower. But at the same time, it can run in the background whilst I do other things. So it's not like going to completely slow down your whole setup. So we can still, for example, like run or desktop whilst this was running before. Now also something that we did is we plugged it into our agent operating system so that we can generate live previews whilst we're building with this stuff. So, for example, we give it a command, well, our local engine inside the agent operating system runs with Quable. So we can run this on three models now, like Quable 5. And then when we say build something out, it will actually preview it so we can see what we've created and then open up the preview. And everything that we create is plugged into our workspace. So, for example, that 3D Dragon game that we just talked about, that is available to preview inside our workspace right here. And then we can come back to everything that we've created, which is pretty cool. Also inside the workspace, we can open it up inside a new tab or we can get the code from it directly. But that's basically a really cool way to build with local models, preview what you've created and then run it on free models as well. Now, obviously Quable, kind of a reference to Fable 5, but that kind of oversells it. So it's based on Quen 3.627B, which is a strong base model from Alibaba. And it's got a fine tune as well. So it's basically Quen 3.627B with a flashy Quable Coda jacket. And then if you're wondering how to run it, so you can't run it from Olama. You would run it with Apple MLX if you're running it on a Mac. But yeah, the stuff that I built with was pretty nice. The only problem was that it's a lot slower. So if you were comparing it to, for example, like Quifos 9B, Quifos 9B is way, way faster than Quable 27B. So that's something to be aware of as well. It's like, yes, it builds better stuff, but it's going to slow you down. However, it's top of our leaderboards when it comes to GoldieBench and the local models we're testing out. And this is something I'm just going to keep building out over time so you can see the comparisons and see how they perform. The cool thing as well, like you can run your agent OS now on free local private models. You don't need Wi-Fi to use these as well, and they're just ready to go whenever you need them. Now, if we have a look, for example, at the same task with Gemma 4, Gemma 4 12B Coda totally failed on that task. So if we click on this, for example, this is the same game and it just it just didn't work. It didn't work at all. The same, for example, with Quifos, Quifos 9B, we tested the same prompt and it just didn't work. Right. It totally failed. So out of everything I've tested, this is the one where stuff we've created actually works full time. And you can see the prompts here on GoldieBench if you want to see how they compare. Even like the landing page itself looks pretty nice, pretty smooth to use, pretty clean. Doesn't look like generic AI slot. And the moving background is quite nice, too. So it is an impressive model from everything I've tested so far. So that's basically it. The thing that I would say all of this is that local AI is moving fast. Models are changing all the time. There's better and better stuff that I'm seeing coming out pretty much every single day. So I feel like it's ramping up right now. Especially with open source models coming out like all these new updates from China, which is pretty cool. So Quable is one model. But if you want the agent OS, which is the operating system that runs any model, local frontier from one dashboard, here's what you get inside. So you get the local Hermes agent engine, which can run free local models. You got agent Kanban in there. You got GoldieBench style testing. We actually have token efficiency playbooks as well. So if you're using paid APIs, you can make sure that's more efficient and use less tokens. We have every CLI plugged into there, a workspace with every build saved and a memory of your whole business built with Obsidian inside the AI Profit Boardroom. So if you want to get the full system for us for the agent operating system, you can get that inside our community. Link in the comments description or just go to the AI Profit Boardroom.com. Inside the community, you can ask questions, get help and support. I personally answer every single question every single day with video tutorial. And then inside the classroom, you can get access to all of our new courses and free trainings, as you can see here. So for example, if you want to go from beginner to expert, you can get that inside this section. If you want to get our agent operating system, you can get that over here. If you want to learn more about the new stuff, we have new videos, tutorials and guides released every single day. And we date them so you know that they're actually new. And then inside the calendar, you can jump on weekly coaching calls, get help and support in real time. Inside the map, you can meet people in your local area who are building with AI agents. That's all available. Link in the comments description or just go to the AI Profit Boardroom.com. Thanks for watching.