What IDE to use for local models

Hi people,

I am looking for a lightweight IDE or plugin that won't inject large context at initiation.

I tried Cline and native VS Code but they inject such heavy initial context that it fills up my gpu and either goes oom or spend most of my time compacting. The only one I found modestly successful was continue.dev plugin but it needs constant approvals. My use case is to demo/try "autopilot" agent coding.

Thank you!

Some context: I have a 12gb rtx cuda and trying to run any model that would fit. I have a small context available due to the size of the vram.