# 🚀 LM Studio + Qwen 3.6

[Stan Duraham]

The local models have more limitations and are probably best used on the most trodden paths. I bit the bullet and laid down 400 smacks to upgrade to 64GB. That gives me the max context window. The context length is the amount of information that stays live. If you run out of context, AI stops. Now I can keep the same project open as long as I want and keep building on it or drop a file and start from there. It uses over 50GB.

I tried building an editor in C and C++ using GCC on Windows. Bad idea because that's going through one compiler that has to translate code written for another compiler. Lots of flags, typedef and macros. It does find mistakes and makes corrections. Better to use MS compiler for Windows code.

PowerBASIC might do pretty good because it hasn't changed in a long time.

If I tried to write a Windows application with FreeBASIC using its library, I'd probably have the same problem. FreeBASIC -> GCC -> MS compiled code.

I tried building an editor in FreeBASIC using José Roca's library. I gave it too much and didn't have enough context memory. Qwen 3.6 really liked José's code.

I suspect that Qwen 3.6 might do well on José's library with enough context memory because it's a complete wrapper. The only problem there is me. You're expecting a lot of local models to write code on a library you don't have a good grasp of. But the combination might be a good way to learn it.

I'm going to play around with it. There's a lot there, just have to figure out how to use it to your advantage.

[Theo Gottwald]

@Stan Duraham If you do not want to buy a Kimi-Coding Plan (its very helpful and keeps costs accountable) then i suggest you install "Open Code CLI" and use SpecKit. And of course use Qwen 3.6 maybe the Q4 if possible or try a little smaller. Having enough RAM is crucial.


🚀 Good alternative if you don't want to buy a Kimi Coding Plan

If you do not want to buy a Kimi Coding Plan — even though it can be very helpful for coding workflows — then I strongly suggest this setup instead: 👇

1) Install OpenCode CLI 💻
OpenCode is a very interesting coding agent for terminal-based workflows and a strong option if you want a more flexible setup.

Official links:
• OpenCode](https://opencode.ai/]OpenCode) Website
• OpenCode](https://opencode.ai/docs/]OpenCode) Docs
• OpenCode](https://opencode.ai/download/]OpenCode) Download
• OpenCode](https://github.com/opencode-ai/opencode]OpenCode) GitHub

2) Use Spec Kit / Spec-Driven Development 🧠
Instead of jumping straight into code, use Spec Kit to structure the work properly:
requirements ➜ plan ➜ tasks ➜ implementation.
That often gives much cleaner and more controllable results, especially for bigger coding projects.

Official links:
• Spec](https://github.com/github/spec-kit]Spec) Kit GitHub
• Spec](https://github.github.com/spec-kit/]Spec) Kit Docs
• Spec](https://github.github.com/spec-kit/installation.html]Spec) Kit Installation Guide
• Spec](https://github.com/github/spec-kit/releases]Spec) Kit Releases

3) For the model, try Qwen3.6 ⚙️
I would absolutely test Qwen3.6.
If possible, try a Q4 / 4-bit quant. If that is too heavy for your machine, go a bit smaller.

Official Qwen links:
• Qwen3.6](https://github.com/QwenLM/Qwen3.6]Qwen3.6) GitHub
• Qwen3.6](https://huggingface.co/Qwen/Qwen3.6-35B-A3B]Qwen3.6) Official Hugging Face Model
• Qwen3.6](https://qwen.ai/blog?id=qwen3.6-35b-a3b]Qwen3.6) Release Blog
• Qwen](https://chat.qwen.ai/]Qwen) Studio

Useful GGUF / local-model related link:
• LM](https://huggingface.co/lmstudio-community/Qwen3.6-35B-A3B-GGUF]LM) Studio Community GGUF for Qwen3.6

4) Very important: RAM matters a lot 🧩
Having enough RAM / VRAM is crucial.
A local coding model may look great on paper, but if your machine is too tight on memory, the experience quickly becomes frustrating:
slow responses, swapping, unstable generation, and poor usability.

So my advice is:

✅ Best path without Kimi:
• OpenCode CLI
• Spec Kit
• Qwen3.6
• preferably a Q4 quant if your hardware can handle it
• otherwise choose a slightly smaller model or smaller quant

5) If you still want to look at Kimi 📌
For anyone who still wants to compare first:

• Kimi](https://www.kimi.com/code/docs/en/]Kimi) Code Docs
• Kimi](https://www.kimi.com/membership/pricing]Kimi) Pricing

My personal recommendation: 🔥
If you want a setup that is powerful, structured, and cost-conscious, then:
OpenCode CLI + Spec Kit + Qwen3.6 is absolutely worth trying.

It gives you:
• a solid coding interface
• a much better workflow structure
• more control over how you work
• and, with the right hardware, a very strong local or semi-local coding setup

🚀 In short:
No Kimi Coding Plan?
Then install OpenCode CLI, use Spec Kit, and run Qwen3.6 — ideally in Q4 if your RAM allows it.

If your RAM is limited, go a little smaller — but definitely keep the same workflow idea. 👍

PS: I verified the current official pages for **OpenCode**, **Spec Kit**, **Kimi Code**, and **Qwen3.6** before drafting this. OpenCode is currently offered as a terminal tool, desktop app, and IDE extension; Spec Kit's maintainers explicitly recommend installing it from the official GitHub repo; and Qwen3.6 is an official current model line with official weights on Hugging Face and ModelScope. ([OpenCode][1])

[1]: https://opencode.ai/docs/ "Intro | AI coding agent built for the terminal"

[Theo Gottwald]

I got it it finally running.



The trick is:


Which needs a new Sindbyte 01.exe V. 1.9.10  or higher that will be available after further fixes in the next days.

Making Open Code use the MCP-Server while beeing connected to Paperclip is not easy because it would need to use an API-Key for LM-Studio, else LM-Studio will NOT allow usage of its MCP-Servers.

But Paperclip does not want to do that.

So what we do is, that Sindbyte Server will ""Inject"" the API-Key for LM-Studio transparently.
And this way I got my Trading Company running.

They got $50 to waste lets see what they can make out of it. One thig is sure - they will do it better then me.

Note: I did not personally set up the Paperclip, i had Kimi-Code do that. Its enough just to found the company manually, and go to the CEO, generate there an API.Key and hand that over together with the Company ID-Number to Kimi-Code. He can then use the API and manage the company.

[Zlatko Vid]

I tried building an editor in C and C++ using GCC on Windows

I do same thing using Z.ai and in C
and Z.ai make it ..

[Stan Duraham]

Thanks for information. I'm totally new at this but starting to get the picture. I have I5, no vram, 64GB ram.

qwen3.6-35b-a3b appears to be very good, however, its training date ended in 2024. It can't be used for FreeBASIC code.

For C and probably C++, qwen/qwen3-coder-next local model is faster and appears to be pretty good with C.

Using qwen/qwen3-coder-next , I asked it, "Using C compiler to be compiled with GCC on windows, please build a resizable Windows application with a browser in it supporting IWebBrowser, not IWebBrowser2."
It immediately started spitting out code. Two errors. Sent them back one at a time and then it compiled and worked.
However, it told me that GCC can have a problem with COM. So, I'm going to try it again with MS compiler.

But that's powerful to build working COM code using C. I realize heavy metal AI would be better.

[Theo Gottwald]

@Stan Duraham I am using further developed code from you in many projects especially HLIB3.
SO i also would share with you. I am currently working on something all new,

That can save you tons of work and may also work with your perfered language - because you can give it the syntax as context.
Send me your E-Mailadress to my mail then I can give you something for testing, soon.
It needs Sindbyte-MCP-Server and LM-Studio as Backend.

Of course it would work best with a Kimi-Coding Plan, but even without it should be ok.

Eventually it will also work with only LM-Studio then it will need an LM-Studio API-Key.
thats because there is an Limitation in LM-Studio, you can not access it via API AND use its installed Tools if you do not use an API-Key.

If you have that it will work "overnight" on your projects and develop and optimize them.
Using a new Experts System.

I am current testing #Speckit, #BMAD and such tools.
But none of them really gets a project done from A to Z so i am doing something myself.

It is designed that you can give "code context" to the used programming language, and once that is done the AI can work in your "code-style". It may be slow if your computer is cheap.
But it can work while you do something else or while you sleep.

But before you do that get SindByte MCP-Server & LM-Studio and work a little bit with that and LM-Studio so you get an idea what this is all about.

[Theo Gottwald]

@Zlatko Vid

I tried building an editor in C and C++ using GCC on Windows

I do same thing using Z.ai and in C
and Z.ai make it ..

I also like Z.ai but in agentic coding with PowerBasic Code, I prefer Kimi K2.6.

You will see this, if you often use a AI of some Kind, its like "with a person"
You get used to that AI's style and you can get most out of it.
Like a Person an AI also has a character. And you need to adapt to that.

So you seem to have adapted to Z.ai - i think they also have good coding plans.
i have used their local models in the past but currently Qwen is too strong.

Noone beats Qwen 3.6, even their "Coding Plan" is permanently sold out.
You can not buy it (maybe with some luck in the evening at 18 PM?).

Strange fact if you know that Alibaba is behind Qwen and they can not get enough Computing Power.

[Stan Duraham]

I'm learning. Bottom line, must use heavy metal for AI coding.
qwen/qwen3-coder-next local model might be good for some C and C++, but it can't solve infrastructure problems needed to run the code, does give hints and makes corrections. It starts spitting out code in just a few seconds.

I asked qwen/qwen3-coder-next to build an embedded browser for use as a Single Page Application (SAP), in C. The application resides in the browser and text and HTML is injected to change it on the fly. I asked it to build the infrastructure to support interaction with JavaScript and be able to transfer large amounts of text and HTML, converting everything to C strings. It built it and Visual Studio reported no errors. However, it wouldn't compile because I didn't have paths to the proper include files, plus it needed a DLL. It was getting too complicated, so I abandoned the idea. It may/not have worked if I had provided the proper paths and installed or found the DLL.
Good learning experience.

[Theo Gottwald]

@Stan Duraham

For professional coding a coding plan and Kimi Code is actually a good "ToGo" but what you experience is just what i described.
Whatever you do, the KI will bring you a way forward and - in large projects loose the context.

Thats because only a fraction of the available context window can really be used for an task and for very large projects the current AI's get lost with the project complexity.

Without going into details, you will see that this will be much better with a coding plan - BUT the AI will still need you all 500 steps to confirm or correct direction.

And then you get there where I am now, you try Speckit, Openspec and other Systems and you find it will not really solve the underlying problem.
Because the only solution is to break the project in small parts with clear Interfaces and have the AI work on each part separate in a way that the whole smaller part can really fit into the context.

And the context for that is realistically < 200 kb maybe half of that. "Needle in the hystack Test".



Lets see how far I get with my own solution.

My target is complete autonomouse coding.
And the point is - if you manage to split the large task in small enough parts with clear enough interfaces then you can also use local AI.

AI might do some things automatic, but its not yet Aladins Wonderlamp. Even if you use SindByte :-) you still need to understand what you are doing.
And do it in the right way. So programming has not changed in the way that its an art in itself, it just made you the boss of a very fast but somehow limited Team.
And we are all still learning how to manage this best.