[cpburns2009]

Does llama.cpp support Qwen3.5 yet? When I tried it before, it failed saying "qwen35moe" is an unsupported architecture.

[hnfong]

Yes, but make sure you grab the latest llama.cpp release

New model archs usually involve code changes.

[sowbug]

If you're running Ollama, you'll have to wait a little longer for its embedded version of llama.cpp to catch up. It can be a couple days or weeks behind.

[cpburns2009]

Awesome! It looks like the llama.cpp-hip AUR was updated today to b8179, and it works.

[reactordev]

You would need the Dynamic 2.0 GGUF as discussed in the article.

But mmmmmm, Q8_K_XL looks mighty nice.