CYFRAGOVPL/PLLuM-12B-base-2512

TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jan 15, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

PLLuM-12B-base-2512 is a 12 billion parameter base language model developed by the PLLuM consortium and continued by HIVE AI, specialized in Polish with additional English data. Built upon Mistral-Nemo-Base-2407, it features a 32768 token context length and is trained on extensive, high-quality Polish and English text corpora. This model excels in general language tasks and is particularly optimized for applications within Polish public administration, demonstrating state-of-the-art performance in Polish-language tasks.

Loading preview...

PLLuM-12B-base-2512: A Polish-Specialized LLM

PLLuM-12B-base-2512 is a 12 billion parameter base model from the PLLuM family, developed by the PLLuM consortium and further advanced by HIVE AI. This model is built on the Mistral-Nemo-Base-2407 architecture and is uniquely specialized for the Polish language, incorporating additional English data for broader generalization. Its development involved extensive data collection, rigorous cleaning, and deduplication of large-scale Polish and English text corpora.

Key Capabilities

  • Polish Language Specialization: Developed with a focus on high-quality Polish text data, achieving state-of-the-art results in Polish-language tasks.
  • Robust Training: Continued-pretrained on ~6.7 billion whitespace tokens from Polish and English corpora.
  • Foundation Model: Serves as a base model for further fine-tuning, with instruction-tuned and chat-aligned variants available within the PLLuM family.
  • RAG Optimization: Designed to perform well in Retrieval-Augmented Generation (RAG) settings, with a specific prompt format for document-based question answering.

Good for

  • General Language Tasks: Text generation, summarization, extraction, and question answering in Polish.
  • Domain-Specific Assistants: Particularly effective for applications in Polish public administration, legal, and bureaucratic contexts.
  • Research & Development: A strong building block for AI applications requiring robust Polish language understanding and generation.

Finetunes
1 models