module name

[Mrship12138]

May I ask what my model name should be filled in when I use the local Olama to build qwen2.5-coder: 32b

[Chenglong-MS]

For Qwen2.5-coder:3b the configuration is as follows (key is left empty):

SO I think the 32b model the configuration should be the same, by replacing model name to qwen2.5-coder:32b

[Mrship12138]

Excuse me, my machine configuration is 32G+4060ti 16G. Which model would have better performance when used locally?
If attempting to run ollama run deepseek-coder-v2, select whether the model is configured as shown in the image