Hacker News new | ask | show | jobs
by ako 65 days ago
That is not what i'm seeing. I've been coding intensively with claude code for the last 3 months: 200k lines of go, 1200+ commits, mostly using opus. I don't think i could have done this with a local LLM. Maybe on a M5 pro?
1 comments

Qwen 3.5 122b is competitive with Opus 4.6, and runs at 35t/s on a Strix Halo. It is my daily driver.

Unlike Opus I can run abliterated models with censorship removed so it can be used for security research and reverse engineering and whatever I want with privacy, offline.

It makes any hosted models feel like a kids toy.