PLLuM
Poland's national sovereign LLM family, from 8B to 70B, for public administration and business.
About
PLLuM (Polish Large Language Model) is a national research program that produced Poland's first fully native large language model family. Led by Wroclaw University of Science and Technology with NASK, the National Information Processing Institute, two Polish Academy of Sciences institutes, and the University of Lodz, it is funded by the Ministry of Digital Affairs and trained on a cluster of over 300 NVIDIA H100 GPUs. The family ranges from 8B to 70B parameters and includes mixture-of-experts and retrieval-augmented variants.
The project is explicitly framed as sovereign infrastructure: transparent data governance, alignment with the EU AI Act, and models meant to power Polish public services and businesses rather than just research demos. Presented publicly in February 2025 and awarded a national digital-transformation prize later that year, PLLuM sits alongside Bielik as one of the two pillars of Poland's domestic LLM ecosystem.
Specs
Context window
Pricing
Free quota
API access
Weights
Released
Benchmarks
Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.
Use cases
Trust score — 7/10
Scored 7/10 (metrics tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 96; Trending score 70/100 from researcher assessment.