https://huggingface.co/tencent/Hy-MT2-30B-A3B

#2466
by kalle07 - opened

https://huggingface.co/tencent/Hy-MT2-30B-A3B

7b allready done by
unsloth/Hy-MT2-7B-GGUF

Model HYV3ForCausalLM is not supported
TIME: Sat May 23 12:11:13 2026

but let's try again on the next update. remind me in couple of days please

Model HYV3ForCausalLM is not supported
TIME: Sat May 23 12:11:13 2026

but let's try again on the next update. remind me in couple of days please

Please check if there is an opportunity available.
Thank you

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#Hy-MT2-30B-A3B-GGUF for quants to appear.

hmmm still
2000 61 si Hy-MT2-30B-A3B error/1 ~HYV3ForCausalLM

may this work
litigerking/Hy-MT2-30B-A3B-GGUF

hmmm still
2000 61 si Hy-MT2-30B-A3B error/1 ~HYV3ForCausalLM

may this work
litigerking/Hy-MT2-30B-A3B-GGUF

I was unable to load any of the GGUFs in LM Studio that were presented on HF.
I assume that the model provider had reasons for not providing these quanta.
The structure of this specialized model may be too complex.

The existing ggufs may be generated by a fork of llamacpp. This is exactly the reason we are using only main llamacpp is to not confuse the user

Sign up or log in to comment