mradermacher

/

model_requests

like 140

Thanks @MuXodious !

It's queued!

You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#MS3.2-24B-Magnum-Diamond-PaperWitch-heresy-GGUF for quants to appear.

There has been an error in this quantisation process.

 -6966   48  I MS3.2-24B-Magnum-Diamond-PaperWitch-heresy   error/47 1/24,Q2_K

Some models can be too claustrophobic to fit inside a tiny Q2 or less.

Thanks a lot for letting me know. No worries I fixed it. I updated llama.cpp and it is working now:

-6966   48  I MS3.2-24B-Magnum-Diamond-PaperWitch-heresy   run/imatrix 1/24,Q2_K [17/363]

Not sure if the old llama.cpp version had a issue or if it simply broke due to it trying to start quantizing exactly while llama.cpp was updating.