Evidence-backed European AI register
Sapienza NLP Group, Sapienza University of Rome
Reviewed identity, roles, model listings, pricing and evidence for Sapienza NLP Group, Sapienza University of Rome.
Dataset compiled 2026-08-27 · evidence over inference
Reviewed identity
- Headquarters scope
- EU headquarters
- Headquarters record
- Rome
- Legal entity
- university research group (public university)
- Ownership
- public research
- Founded
- unknown
- Confidence
- high
- Last verified
- 2026-08-22
Evidence boundaries
Organisation listings identify a reviewed canonical record. Model listings show an association in the source register; they do not by themselves establish model creation, current API availability, hosting location or infrastructure ownership.
Model listings
- Type
- text
- Parameters
- 7B
- Context
- 4,096 tokens
- Languages
- Italian and English (plus code)
- Licence
- Apache-2.0
- Release
- 2024-12
- Type
- text
- Parameters
- 3B
- Context
- unknown
- Languages
- Italian, English
- Licence
- Apache-2.0 (family)
- Release
- 2024
- Type
- text
- Parameters
- 1B
- Context
- unknown
- Languages
- Italian, English
- Licence
- Apache-2.0 (family)
- Release
- 2024
- Type
- text
- Parameters
- 350M
- Context
- unknown
- Languages
- Italian, English
- Licence
- Apache-2.0 (family)
- Release
- 2024
- modello-italia-9b (hosted mirror)
- Type
- text
- Parameters
- 9B
- Context
- unknown
- Languages
- Italian
- Licence
- unknown
- Release
- unknown
Profile note
The first LLM family pretrained from scratch on Italian, and one of the few genuinely 'truly-open' European efforts (data as well as weights). No commercial API — public research only, funded by Italy's PNRR FAIR programme with CINECA compute. ChatMinerva is a public demo assistant, not a paid product. Note the tight 4,096-token context window on the 7B, which limits practical deployment versus Velvet 14B (128k).
Record sources
- https://huggingface.co/sapienzanlp/Minerva-7B-instruct-v1.0
- https://huggingface.co/sapienzanlp/Minerva-7B-base-v1.0
- https://huggingface.co/sapienzanlp/Minerva-3B-base-v1.0
- https://huggingface.co/sapienzanlp/Minerva-1B-base-v1.0
- https://nlp.uniroma1.it/minerva/
- https://www.uniroma1.it/en/notizia/ai-made-italy-here-minerva-first-family-large-language-models-trained-scra…
- https://nlp.uniroma1.it/