Qwen3-Coder-Next

Re:Qwen3-Coder-Next by mark_l_watson on Tuesday February 03, 2026 @05:47PM (#46878493)

I configured Claude Code to use a local model (ollama run glm-4.7-flash) that runs really well on a 32G M2Pro macmini. Maybe my standards are too low, but I was using that combination to clean up the code, make improvements, and add docs and tests to a bunch of old git repo experiment projects.

[ Parent | on HN ]

Re:Qwen3-Coder-Next by redundantly on Tuesday February 03, 2026 @08:33PM (#46880209)

Did you have to do anything special to get it to work? I tried and it would just bug out, things like respond with JSON strings summarizing what I asked of it or just outright getting things wrong entirely. For example, I asked it to summarize what a specific .js file did and it provided me with new code it made up based on the file name...

[ Parent | on HN ]

Re:Qwen3-Coder-Next by mark_l_watson on Tuesday February 03, 2026 @08:38PM (#46880253)

Yes, I had to set the Ollama context size to 32K

[ Parent | on HN ]

Re:Qwen3-Coder-Next by redundantly on Tuesday February 03, 2026 @10:13PM (#46881001)

Thank you, it's working as expected now!

[ Parent | on HN ]