alt Hacker NewsAnd we're off! It's working great with DeepSeek V4, although DeepSeek V4 Pro tends not to really run into problems anyway being near-frontier, but I definitely see improvement with Flash.
Replies
zambelli • today at 3:56 AM
That was fast! It's great to hear it's working well :)
Did you notice any particular guardrails firing? Always curious about things I haven't tested on - especially if it has a different shape.
Hi! I'm using DeepSeek V4 Flash on high via opencode.
It should work with opencode using the proxy server or middleware method right? Any tips?
Does this need a GPU to work? Or is it CPU only? I ask because I plan to try to run this using Docker. But I have a modest RTX 5070 12GB VRAM.
Or maybe I could use opencode as a remote backend too?
I'm thinking of trying the OpenAI-compatible provider route: https://opencode.ai/docs/providers/#custom-provider