tencent/EVIE-Preview-4.5B
#2856
by mku1988 - opened
It would be great if you could generate quants for:
https://huggingface.co/tencent/EVIE-Preview-4.5B.
I hope they can be run by llama.cpp since its made using Qwen 3.5 4B but uses the ColPali Engine as its reference implementation.
Dont know if it will work but...
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#EVIE-Preview-4.5B-GGUF for quants to appear.
Thank you. looking forward to testing it as soon as its done. Is your server alright. Nothing seem to be running.
EVIE-Preview-4.5B INFO:hf-to-gguf:Model architecture: ColQwen3_5
EVIE-Preview-4.5B ERROR:hf-to-gguf:Model ColQwen3_5 is not supported
pretty expected. until it's merged into main llamacpp we cant quant. server is alright, the model isnt
Thank you. Hopefully it will besupported soon.
mku1988 changed discussion status to closed