←back to thread

Ask HN: Cursor or Windsurf?

310 points skarat | 1 comments | 12 May 25 04:41 UTC | HN request time: 0.001s | source

Things are changing so fast with these vscode forks I m barely able to keep up. Which one are you guys using currently? How does the autocomplete etc, compare between the two?
Show context
monster_truck ◴[12 May 25 07:17 UTC] No.43960400[source]▶
Void. I'd rather run my own models locally https://voideditor.com/
replies(1): >>43960805 #
traktorn ◴[12 May 25 08:31 UTC] No.43960805[source]▶
Which model are you running locally? Is it faster than waiting for Claudes generation? What gear do you use?
replies(2): >>43962562 #>>43964972 #
1. monster_truck ◴[12 May 25 16:42 UTC] No.43964972[source]▶
That's the fun part, you can use all of them! And you don't need to use browser plugins or console scripts to auto-retry failures (there aren't any) or queue up a ton of tasks overnight.

Have a 3950X w/ 32GB ram, Radeon VII & 6900XT sitting in the closet hosting smaller models then a 5800X3D/128GB/7900XTX as my main machine.

Most any quantized model that fits in half of the vram of a single gpu (and ideally supports flash attention, optionally speculative decoding) will give you far faster autocompletes. This is especially the case with the Radeon VII thanks to the memory bandwidth.