News for hackers. Stuff that matters.
Re:Ask HN: Has anyone replaced Claude/GPT with a local model... by xmstan on Tuesday June 16, 2026 @05:08AM (#48552563)
Yes, we use Qwen 3.6 27B Q6_K. We use it on Radeon R9700 32GB and it delivers 50tps with MTP. We compare it to Sonnet from 4-6 months ago when it comes to output. Totally usable for daily coding.

There are no comments on this comment yet.