mradermacher

/

model_requests

like 126

It's queued!
It actually already got queued as highly anticipated model a while ago.

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#Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-GGUF for quants to appear.

Oh I see what's happening. It is blocked due to beeingof the Qwen3NextForCausalLM archidecture whose llama.cpp support currently having has some major issues as stated by mradermacher:

just a heads-up, it seems we are acquiring a lot of qwen3next models, which llama.cpp claims to support, but just crashes in various ways in convert_hfd_to_gguf.py or later.

It will be processed once thouse issues are resolved.

Thank you very much