Deepseek v4 pro! Top up your credit as you go and they're having a sale until May 31st, but even without the sale 1M output tokens is "only" 3.48. Flash is only 0.28 per 1M output.

[–] chesmotorcycle@lemmygrad.ml 2 points 2 days ago

Not sure if I could swing Deepseek at my job tho. Surprisingly, Cursor still comes with Kimi2 as model option, so there's that.

[–] yogthos@lemmygrad.ml 2 points 2 days ago* (last edited 2 days ago) (1 children)

If you have the memory, I can highly recommend Qwen3.6-35B-A3B-Q8. It's hands down the best local model I've tried. It only loads 3b params in memory too, so should run with 16gb, or you can drop to a lower quant too.

[–] chesmotorcycle@lemmygrad.ml 2 points 2 days ago

I think I tried qwen3.6 but the 8B version, and that tanked my 16GB. But I'll give the smaller one a shot!