AI Briefing#domyn
The latest AI and developer news about #domyn, with the original source and a short summary.
The latest AI and developer news about #domyn, with the original source and a short summary.
Developed with Fraunhofer using NVIDIA GH200 GPUs, the Mixture-of-Experts model targets all 24 official EU languages.
The team optimized FSDP and Expert Parallelism on 384 GH200 GPUs to reach 1,300 tokens/s per GPU, overcoming inter-node bandwidth bottlenecks.
The 10B-parameter model uses roughly 2-4x fewer reasoning tokens than leading peers while maintaining comparable accuracy.
Italian startup Domyn has announced plans to develop a large-scale 400B model for European AI sovereignty.