User Tools

Site Tools


ai:formats-faq

This is an old revision of the document!


DISCLAIMER

No guarantees are provided as to the accuracy of this information. I do my best but things move fast and this is hecking hard to figure out.

What hardware works?

  • Nvidia newer than FIXME
    • 30XX, 40XX. (10XX? 20XX? Idk)
  • AMD newer than FIXME
    • things known not to work: multi-GPU
  • Intel
    • I don't have anything working yet, but it's supposed to be possible to run things on an A770 with Intel's SDK.

So what's up with LLM formats?

  • GGUF - CPU only
  • GPTQ - GPU only; if it doesn't fit in VRAM you can't load it. Works with FIXME

How much VRAM do I need?

  • Usually about 1 GB more than you have.
ai/formats-faq.1699717911.txt.gz · Last modified: 2023/11/11 15:51 by naptastic