GoThread
appearance log in
home all local communities
T

@TiredDinoByte@lemmy.today

@TiredDinoByte@lemmy.today

member since 13 Apr 2026 21:22 · modlog

postscomments
  • on Anthropic confirms new Claude Code limits to prevent game cloning — users report Opus 5.5 is also actively blocking reverse engineering tasks in c/technology@lemmy.world · 3 Nov 2026

    I think you are right, but that seems VERY unenforceable.

  • on Sam Altman Absolutely Hates the Idea of People Running Their Own AI Models at Home, Argues They Shouldn’t Own Computers: He'd prefer if we surrender all our RAM to data centers. in c/technology@lemmy.world · 30 Oct 2026

    I’ll have to try that, for my part qwen-3.8-flash-next has been a world of difference

  • on Need to make a fire playlist. in c/animemes@ani.social · 29 Oct 2026

    Gravity, Wicked

  • on Anthropic logged net loss of over $80 billion in first half of 2026 in c/technology@lemmy.world · 21 Oct 2026

    I won’t pretend to be an expert but my understanding is that the architecture loads experts from the SSD on demand with the RAM serving as a hot cache and the VRAM running the active experts.

    As I said above I was able to run 70tok/s on my 4090w64GB ram and a samsung pcie4.0 ssd.

    I haven’t run the benchmarks myself, but I can say the quality of response I was getting seemed on par with the frontier models I use for work (Claude opus/fable) and the published benchmarks for the model compete with those same models.

    It is a q3 quantization so there is some small loss of accuracy, but from what I’ve understood those are modest losses in the worst case.

  • on Anthropic logged net loss of over $80 billion in first half of 2026 in c/technology@lemmy.world · 21 Oct 2026

    Qwen3.8-flash-next broke the vram requirement with its new architecture (which is a preview of their 4.0 architecture). You can run a 177b parameter model on 12gb VRAM, 64gb ram and 80gb SSD at 30tok/s and the speed scales almost linearly with increases to vram.

    Incidentally, this was proven at almost the exact time all the calls for “regulating local models because they’ll spread into the toasters” started.

    You absolutely can have local models that run on consumer grade hardware, and the proprietary companies know it and are scared to death.

GoThread · self-hosted threadiverse · instances · modlog · rss · appearance · AGPL-3.0