swiss-ai/Apertus-8B-Instruct-2509

#1435
by hikkyy - opened

Llama cpp has merged apertus architecture support just now, so we can get quants for this
https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509

I already asked about them under https://huggingface.co/mradermacher/BabyHercules-4x150M-GGUF/discussions/7#68debd8b4da22bedaa1a7de5 but let's copy that message here so everyone sees which of them I already intend on queueing. Next time I will make a dedicated discussion for such a highly anticipated model again instead of abusing BabyHercules for it.

@mradermacher Please update llama.cpp to the latest version of our fork then queue:

hikkyy changed discussion status to closed

Sign up or log in to comment