Mungert

/

MinerU2.5-2509-1.2B-GGUF

like 0

There is no support for q4 when using llama.cpp to make projector file. q8 is the smallest.

100s is normal. There are a lot of tokens created from an image.

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

thanks，you are right.
I tried compile llama.cpp myself, add openblas and compile flag to optimize, it's slow though.

CPU 上跑还是很慢，一张图100秒以上

I find this frustrating with image model processing and using cpu. all models seem the same. Try Making the image smaller, use more cpu cores. Or if you need realtime a GPU. But you might as well use something other than llama.cpp if you have to use a GPU.

thanks，you are right.
I tried compile llama.cpp myself, add openblas and compile flag to optimize, it's slow though.

if you have a cpu with avx512 support that can give a 30% performance boost.