Introduction

Continuing from the previous blog I will use the same setup as before but evaluate some other models. All the code / Agent chats can be found on Github .

I am going to use Qwopus3.5-9B-coder-Exp-BF16 this is essentially a fine-tuned coding and agent model based on Qwen 3.5 9B. The name breaks down roughly as:

• Qwopus = “Qwen + Opus” (the author’s branding)
• 3.5 = based on the Qwen 3.5 family
• 9B = 9 billion parameters
• coder = specialized for software development tasks
• Exp = experimental build/training variant
• BF16 = full-precision bfloat16 weights (not quantized)

The site says “it has a stronger emphasis on agent workflows and tool use rather than pure code completion.”

Test 3 Mac Qwopus3.5-9B-coder-Exp-BF16

This model https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-GGUF is similar to the last Qwen model but has been re-trained against other open source datasets.

It took a while to generate the results (longer than the last model) it also used all the cores of my machine

The initial Agent Chat generated what seemed like a full app, however on running I got the following errors.

uv run main.py
Traceback (most recent call last):
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 236, in <module>
    main()
    ~~~~^^
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 230, in main
    window = MainWindow()
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 123, in __init__
    self.setCentralWidget(central_widget)
    ^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'MainWindow' object has no attribute 'setCentralWidget'

I fed this back into the model chat and it resulted in the app running.

Hower neither drag and drop of the file load button worked! The error seems to be a bad import

uv run main.py
Traceback (most recent call last):
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 200, in _load_images
    from PySide6.QtWidgets import QFileDialog, QFileDialogOptions
ImportError: cannot import name 'QFileDialogOptions' from 'PySide6.QtWidgets' (/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/.venv/lib/python3.14/site-packages/PySide6/QtWidgets.abi3.so)

I also noted that it seems to be importing within the functions not at the top of the file which is against PEP-8

 def _load_images(self) -> None:
        """Open a file dialog to select and load one or more images."""
        from PySide6.QtWidgets import QFileDialog, QFileDialogOptions

After the next fix it now shows the file dialog but doesn’t show the image, drag and drop doesn’t work due to

uv run main.py
Error calling Python override of QMainWindow::eventFilter(): Traceback (most recent call last):
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 216, in eventFilter
    on_drag_enter(event)
    ^^^^^^^^^^^^^
NameError: name 'on_drag_enter' is not defined

As the context is getting quite large (31K / 66K) I have decided to compact (create a summary) of the input and ask it to fix the problems. You can use the Zed New from Summary button in the agent panel to do this.

[@PySide6 Drag and Drop Image Viewer](zed:///agent/thread/3d9a8f3b-031d-4400-9b6d-58fbfb209ffa?name=PySide6+Drag+and+Drop+Image+Viewer)
When loading an image from file nothing is displayed, when dropping an image I get the following error Error calling Python override of QMainWindow::eventFilter(): Traceback (most recent call last):
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 216, in eventFilter
    on_drag_enter(event)
    ^^^^^^^^^^^^^
NameError: name 'on_drag_enter' is not defined

This next step seem to take an age! The GPU is maxing out and all the cores on my mac are running as is the fan! It seems to be doing some weird stuff for example why do this?

if TYPE_CHECKING:
    from typing import Callable

    from PySide6.QtCore import QObject

It is still running, I am going to do the school run and see what it produces at the end (the advantages of getting AI to do work for you! ) … 30 Minutes later back from the school run it seems to have got stuck in a loop see AgentChat3.md and is just repeating itself (the disadvantage of un supervised AI, how much power did that cost?). To quote the LLM

Actually, I realize I've been going in circles. Let me take a step back and think about what the user is saying.

The app has been left in an un-runnable state, I could git revet it however the agent has ignored all my worktree requests (I am begining to think this is a mac thing as the last mac agent did the same. Will investigate this more in another blog).

I have asked the agent to undo the changes let’s see what happens.

I haven't made any changes to the file yet - you're the first to interact with this file in this conversation. 

If you're referring to changes made by a previous agent in this thread, could you clarify which changes you'd like undone? Please provide:
1. The specific changes you want reverted
2. The file path involved
3. What the original state should look like

Or if you're referring to a different context, please let me know and I'll help you appropriately.

Well that is annoying. Let’s start a new thread and fix the issues.

Fist I pasted the error message

uv run main.py
Traceback (most recent call last):
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 16, in <module>
    from PySide6.QtGui import AlignmentFlag, QDragEnterEvent, QDropEvent, QPixmap
ImportError: cannot import name 'AlignmentFlag' from 'PySide6.QtGui' (/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/.venv/lib/python3.14/site-packages/PySide6/QtGui.abi3.so)
➜  ImageDropMacQwopus3.5-9B-coder-Exp-BF16 git:(main) ✗

It seems to have fixed these issues AgentChat4.md. Now to see if we can get the images to display as both file and drag drop still fail. Lets try a simpler method (I am also going to re-start the server to see if that helps).

I use the simple prompt

[@main.py](file:///Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py) does not display the image when loading from the file dialog. I am using a png

This went down an interesting rabbit hole once I asked it to debug why the image is not loading! Well worth a read of AgentChat5.md It decided to make a smaller program to do a test (including writing a small test image using PIL which I had to install for it, I need to add us uv add to install packages to the AGENTS.md as it got very confused).

On a side note, I now have to go to a meeting, I started teams and it didn’t want to work with audio, once I stopped the server everything worked, I guess this model is using all the resources and can’t do anything else.

Project still not working, will try one last time after the meeting.

Hours later

I have had to re-start the server and give it the current error messages. As I asked it to do some debugging, I have some good info

[DEBUG] Loading image from: /Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/test_images/test.png
[DEBUG] File exists: True
[DEBUG] Is file: True
[DEBUG] File size: 122
[DEBUG] Exception: type object 'PySide6.QtGui.QPixmap' has no attribute 'fromFile'

Seems it is a method not existing, but can it fix it?

So it says it has fixed it AgentChat6.md but

 uv run main.py
  File "/Volumes/teaching/Code/AgenticAdventures/ImageDropMacQwopus3.5-9B-coder-Exp-BF16/main.py", line 216
    continue
    ^^^^^^^^
SyntaxError: 'continue' not properly in loop

Well it seems to run and try to load now,

[DEBUG] WARNING: Loaded image is null!
[DEBUG] Loading image from: /Volumes/teaching/Code/PyNGLDemos/FBODemos/SimpleFBO/SimpleFBO.png
[DEBUG] File exists: True
[DEBUG] Is file: True
[DEBUG] File size: 34590
[DEBUG] Image loaded successfully - size: PySide6.QtCore.QSize(400, 303)

However, nothing has displayed! Let’s tell it

The image loads but nothing is displayed in the app, are you loading it to a widget?

This is not working, I have an app but it doesn’t run, and it doesn’t seem to know how to fix it. Will give up see AgentChat7.md for the final bit.

Test 2 Linux Qwopus3.5-9B-coder-Exp-BF16

As I had to stop the Mac tests to join a meeting, I decided to fire off the same tests using the Linux build.

Used the same setup as before but I had to run the server with the -c 0 flag again to get a big enough context to use it. Again this run very slow, and initially has loads of errors.

As you can see this is using all the GPU resources and running at 100% again. So far it has been running for about 30 minutes without finishing!

40 minutes still running, I could have written this by hand!

1 Hour, getting board now, need to get it to notify me once finished via text as I am on a remote machine!

It’s now got stuck in a loop see AgentChat1.md I will drop the current errors into a file and get it to try and fix it one by one each in a new thread, lets see if a smaller context helps.

It is now failing with

def _on_drag_leave_event(self, event: QDragLeaveEvent) -> None:
                                          ^^^^^^^^^^^^^^^
NameError: name 'QDragLeaveEvent' is not defined. Did you mean: 'QDragEnterEvent'?

I have asked it to fix it but it is still getting lost, may as well do it myself, as it is just an import error for the type hint. Which any AI should get right first time!

Next error is

 self.setWindowIcon()
    ~~~~~~~~~~~~~~~~~~^^
TypeError: MainWindow.setWindowIcon() takes exactly one argument (0 given)

This has continued for a long time with many more errors, I am going to just give up as I Have wasted too long. This model is not suitable for this sort of task.

Conclusion

In conclusion this model sucks! ….

It’s still only a 9B model compared to the 14-32B and 70B+ models.

I should only really expect it to be able to write small functions,explain code or make simple edits. It can’t understanding large codebases, following long instructions (large contexts), or debug across single or multiple files.

For the next project I am going to use Qwen3-Coder-30B-A3B and see how that fares.