Migrated over from Hazzard@lemm.ee

  • 0 Posts
  • 2 Comments
Joined 1 year ago
cake
Cake day: June 28th, 2025

help-circle
  • I’m surprised you feel you need that much. Personally, I’m tinkering on a 7900XTX, with 24Gb of VRAM. I can’t run the massive new models, like the latest Deepseek Flash at 400+ Gb, but neither can 192Gb. Means my context isn’t unlimited, but I’m able to run even big local models like Qwen3.8 at Q4_K_M with a context of 64K, which is enough when paired with a front end like Hermes that can run compaction and invoke subagents. Honestly, I’d describe 24Gb as a sweet spot for local AI usage, 32Gb sounds like comfortable headroom for a larger context window, or even multiple heads.

    To be fair, I guess it is unified memory, and it doesn’t sound like you’re running it on a dedicated machine, so maybe the other stuff you’re running is pushing past 8Gb and giving you less space for AI than me. But 128Gb still sounds like wild excess to me, well into the diminishing returns of slightly more accurate rounding and needlessly large context.


  • Kind of a hyperbolic nothing burger of a headline. The current Xbox uses emulation to support the Xbox, Xbox 360, and Xbox One library. And it doesn’t support the whole library and almost certainly never will, the few remaining titles are likely prohibitively expensive and complicated to support for very niche audiences.

    In other words, this headline is both obvious, who would expect them to not support their emulator on new hardware? And wrong, it won’t support every Xbox game ever made.