Thread

1. reedf1 · 1790785294 · focus · HN ↗

   I've been running Qwen 3.8 27b (an opus 4.6 tier model), locally on a 5090 for just over two weeks @ 170 tokens/s. That's a frontier model from 9 months ago running on consumer hardware. Who knows where distillation and pruning gets us in another year.

   1. oidar · 1790785564 · focus · HN ↗

      What are you thoughts on it's performance compared to 4.6?

      1. reedf1 · 1790786205 · focus · HN ↗

         Indistinguishable or very mildly better. But it's considerably faster. Some portion of that is also probably down to improvements in model harnesses, I've been using opencode.

         1. jeffrallen · 1790789244 · focus · HN ↗

            Yeah, the Shelley agent (from exe.dev) loves Qwen 3.8, they kicked ass on a Django app for me today.

Unofficial Hacker News client; not affiliated with Y Combinator.