Hacker News new | ask | show | jobs
by pxc 315 days ago
NVIDIA will probably give us nice, coding-focused fine-tunes of these models at some point, and those might compare more favorably against the smaller Qwen3 Coder.
1 comments
iJohnDoe 315 days ago
What is the best local coder model that that can be used with ollama?

Maybe a too opened ended question? I can run the deepseek model locally really nicely.

link
bigyabai 315 days ago
Probably Qwen3-Coder 30B, unless you have a titanic enough machine to handle a serious 480B model.
link
pxc 315 days ago
Is the DeepSeek model you're running a distill, or is it the 671B parameter model?
link