Thread

Qwen3.8 Max now ranked as the best overall model by agentic index

420 points · 270 comments · apitman

brcmthrowaway · 1786044113 · focus · HN ↗
Could someone like Apple be playing the long game - Good Enough(tm) intelligence will eventually fit in our pocket and homes?
1. colingauvin · 1786047007 · focus · HN ↗
  DS4 Flash Q2/Q4 mixed quant fits on a DGX Spark (a $4000 device which is not particularly unheard of expense for Apple customers), and is indistinguishable for me from Opus for my personal daily use/assistant benchmarks[0].
  [0]<a href="https://humanparadox.org/local-vs-frontier-benchmarks-for-my-personal-assistant/" rel="nofollow">https://humanparadox.org/local-vs-frontier-benchmarks-for-my... - note here I tested Q8 but have found no difference at lower quant.
  1. dofm · 1786052341 · focus · HN ↗
    Indeed. I like using Macs mostly, and the bargain M1 Max MBP I am using for local LLMs is a fabulous experimentation platform and does loads of other stuff well, so I am in no rush, but if I reached the point of buying dedicated hardware for an LLM, I'd be looking at the DGX Spark machines.

Unofficial Hacker News client; not affiliated with Y Combinator.