Request:https://huggingface.co/moonshotai/Kimi-K2.5
#1827
by testamentaddress01 - opened
https://github.com/ggml-org/llama.cpp/releases/tag/b8003,
Kimi-2.5 Vision support has been added in b8003 version.
(https://github.com/ggml-org/llama.cpp/pull/19170)
Is it difficult to quantize this GGUF?
testamentaddress01 changed discussion title from https://huggingface.co/moonshotai/Kimi-K2.5 to Request:https://huggingface.co/moonshotai/Kimi-K2.5
it's not as difficult, it got merged not that long ago and I dont know how to upgrade the llama cpp, so waiting for nico to upgrade so I can queue it =)
I notified him not that long ago as I just got back from uni lol
Thank you. I understand situation. I'm looking forward to GGUF.
If the upgrade of llama.cpp is completed, it can queue up the GGUF please? I’m looking forward to it.