Hypernova-60B
A compressed language model for agentic workflows and tool use.
Senior LLM Researcher at Multiverse Computing. I train, compress, and optimize large-scale foundation models for both language and vision.
PhD in Natural Language Processing from the University of the Basque Country UPV/EHU, developed at the IXA Group and the HiTZ Basque Center for Language Technologies.
My work spans large-scale training, efficient inference, and model compression. At HiTZ I trained Latxa on the Leonardo Supercomputer using up to 512 GPUs across 128 nodes. At Krea I optimized fine-tuning pipelines for image and video diffusion models with distributed techniques such as FSDP2. Today, I work on making foundation models more efficient at Multiverse Computing.
Exponential Fellow 2025. In my free time I build veridika.ai, an AI agent framework for real-time fact-checking.
Featured Models
All models & code
FLUX.1 Krea
An open image-generation model with a focus on aesthetics and photorealism.
GoLLIE
A language model that follows annotation guidelines to extract information from text.
Latxa
Instruction-tuned language models for Basque, evaluated on language understanding and generation.
Medical-mT5
An open multilingual text-to-text language model for the medical domain.
Veridika.ai
An AI agent framework for real-time fact-checking.
Background
Full career & educationMultiverse Computing
Senior LLM Researcher. Model compression, synthetic training data, and efficient distillation. Training EU-focused large language models from scratch.
Krea
Machine Learning Researcher. Image and video generation, distributed fine-tuning, and artistic image retrieval.
HiTZ · University of the Basque Country
PhD in NLP, advised by German Rigau and Rodrigo Agerri. Cross-lingual learning and language models.
Get in touch
Let’s talk about models.
For research conversations, collaborations, or questions about my work:
igarciaf896@gmail.com