[hexmiles]

If I understood it correctly: this time no, it is actually new engine builded by the ollama team indipendent from llama.cpp

[buyucu]

I doubt it. Llama.cpp just added support for the same models a few weeks ago. Folks at ollama just did a git pull.

[magicalhippo]

It's open source, you could have checked. Seems indeed like the new engine cuts out llama.cpp, using GGML libary directly.

https://github.com/ollama/ollama/pull/7913

[buyucu]

seriously? who do you think develops ggml?

hint: it's llama.cpp

[Havoc]

llama.cpp added support for vision 6 days ago.

See SimonW post here:

https://simonwillison.net/2025/May/10/llama-cpp-vision/

>If I understood it correctly

You understood it exactly like they wanted you to...