Re:Experimenting with Local LLMs on macOS
by bigyabai on Monday September 08, 2025 @11:55AM
(#45169864)
Qwen3 A3B (in my experience) writes code as-good-as ChatGPT 4o and much better than GPT-OSS.
[ Parent
| on HN ]
I just tested Qwen3 A3B vs ChatGPE a random prompt from my head and:
> Please write a C# middleware to block requests from browser agents that contain any word in a specified list of words: openai, grok, gemini, claude.
I used ChatpGPT 4o from GitHub Copilot inside VSCode. And Qwen3 A3B from here: https://deepinfra.com/Qwen/Qwen3-30B-A3B
ChatGPT 4o was considerably better. Less verbose and less unnecessary abstractions.
Re:Experimenting with Local LLMs on macOS
by bigyabai on Monday September 08, 2025 @12:13PM
(#45170089)
You want the 2507 update of the model, I think the one you used is ~8-10 months out-of-date.
Re:Experimenting with Local LLMs on macOS
by jasonjmcghee on Monday September 08, 2025 @07:26PM
(#45175458)
No they want Qwen3-Coder-30B-A3B-Instruct