Re:Ask HN: Has anyone replaced Claude/GPT with a local model...
by codemk8 on Monday June 15, 2026 @06:42PM
(#48548043)
You mean deepseek-v4-flash, right? Same here. I use it for my Hermes agent. It's so cheap that I sometimes feel "guilty". I even put more money than I needed just make sure they do not go out of business.
Re:Ask HN: Has anyone replaced Claude/GPT with a local model...
by ThomasGlanzmann on Tuesday June 16, 2026 @12:55AM
(#48550755)
Yes, I do mean deepseek-v4-flash.
Re:Ask HN: Has anyone replaced Claude/GPT with a local model...
by ThomasGlanzmann on Monday June 15, 2026 @05:05PM
(#48547022)
I do the same. deepseekv4 fast for the 90% of the tasks, if it can't lift it, I use deepseekv4 pro. I use crush as coding agent but removed the blocked commands because I also do a lot of system administration. Love it. I use 8 USD in 7 weeks and use it quiet extensively for all sorts of things, programming, system administration, google search replacement, investments, you name it.
Re:Ask HN: Has anyone replaced Claude/GPT with a local model...
by slvnx on Tuesday June 16, 2026 @08:50AM
(#48554428)
Do you use deepcode, or which cli and/or coding agent you use it with?
Re:Ask HN: Has anyone replaced Claude/GPT with a local model...
by thrownaway561 on Tuesday June 16, 2026 @04:43PM
(#48561764)
No... I just use the github copilot chat
67M Ouput 51M Input
Total $0.83 dollar.
I honestly don't understand why people just don't use DeepSeek.