Post History

Current VersionMay 12, 2026 at 12:31

I built a version of the Northwind app using a previous generation qwen3-coder-30b-a3b-instruct model:

Even though this model runs at a much faster token per second rate, the whole development process took much longer to complete, because the model was less efficient, had to think more for each step, and required more manually entered prompt iterations. In the end, even the though most of the functionality was finished, the model never completed the chart features, even when specifically prompted. The total context used was also significantly higher at 83%. Additionally, that older version of Qwen coded used an older version of Flask, which produced some deprecation warnings when the app ran (nothing fatal, but something to be aware of).

The experience with Qwen 3.6 35a3 is just so much better. As a reminder, this is the Northwind demo created by 35a3, with just 2 prompt iterations:

http://1y1z.com:3929

Version 2May 12, 2026 at 12:31

I built a version of the Northwind app using a previous generation qwen3-coder-30b-a3b-instruct model:

http://1y1z.com:8429/customers

Even though this model runs at a much faster token per second rate, the whole development process took much longer to complete, because the model was less efficient, had to think more for each step, and required more manually entered prompt iterations. In the end, even the though most of the functionality was finished, the model never completed the chart features, even when specifically prompted. The total context used was also significantly higher at 83%. Additionally, that older version of Qwen coded used an older version of Flask, which produced some deprecation warnings when the app ran (nothing fatal, but something to be aware of).

The experience with Qwen 3.6 35a3 is just so much better.

Version 1May 12, 2026 at 11:51

I built a version of the Northwind app using the previous generation qwen3-coder-30b-a3b-instruct:

http://1y1z.com:8429/customers

Even though this model runs at a much faster token per second rate, the whole development process took much longer to complete, because the model was less efficient, had to think more for each step, and required more manually prompted iterations. In the end, even the though most of the functionality was finished, the model never succeeded with the chart features, even when specifically prompted. The total context used was also significantly higher at 83%. Also, that older version of Qwen coded used an older version of Flask, which produced some deprecation warnings when the app ran (nothing fatal, but something to be aware of).

The experience with Qwen 3.6 35a3 is just so much better.

Previous Versions