Polish, open ecosystem of language models.
We build AI models, tools, and datasets that strengthen Poland's and Europe's technological sovereignty. Bielik runs locally, understands Polish language and context, and its ecosystem is developed by the SpeakLeash Foundation, partners, and the community.
Where to start?
Four most common paths through the Bielik.ai ecosystem — choose the one that matches your role.
I want to test Bielik
Explore the model's capabilities in the public chat and see how it responds in Polish — no installation, in the browser.
Open chat.bielik.ai 02 · LocalI want to run Bielik locally
Download the model and run it via Ollama, LM Studio, llama.cpp, or vLLM. Everything runs on your hardware, without the cloud.
Quickstart & models 03 · BuildI want to co-develop Bielik
Join the community on Discord, contribute on GitHub, test models in the Arena, develop data and documentation.
Join the communityPolish model. Local deployments. Openness without compromise.
Polish language and local context
Training on a high-quality Polish corpus, custom tokenizer, Polish benchmarks — the model understands inflection, cultural context, and specialized vocabulary.
Local deployments
Models run on your own hardware, on-premise and in isolated environments. No data leakage to external clouds.
Data control
Full sovereignty over prompts, contexts, and results. Audit, governance, and compliance with organizational policies — under your control.
Openness and transparency
Model weights, model cards, arXiv publications, benchmarks, and training data — all documented and publicly available.
European technological sovereignty
Part of an independent AI infrastructure for Poland and the European Union. Open foundations instead of dependence on single vendors.
Ecosystem, not just a model
Research, community, safety, evaluation tools, Bielik Arena, Data Dashboard, deployment partners — complete infrastructure around the core model.
The Bielik model family
From lightweight models running on CPU to advanced variants with instruction tuning and tools — choose the version suited to your needs and hardware.
Who is already using Bielik?
Companies
- RAG on company documents
- Internal assistants
- Sensitive data anonymization
- On-premise deployments
- PoC in 2–6 weeks
Public administration
- Technological sovereignty
- Government assistants
- Citizen Bielik
- Sensitive data locally
- AI education & competencies
Science & community
- Open weights & model cards
- 6 arXiv publications
- Open PL LLM Leaderboard
- Bielik Arena
- Data Dashboard SpeakLeash
Bielik is more than just an LLM. It’s a comprehensive ecosystem.
Around the model core, a network of tools is growing: chat, safety classifiers, community evaluations, data dashboard, civic projects.
Chat Bielik
Public chat for testing the model in the browser — chat.bielik.ai.
SafetyBielik Guard / Sójka
Family of safety classifiers for Polish content moderation.
CommunityObywatel Bielik
Civic project supporting the development of Polish LLM through the community.
ToolsBielik Arena
Community evaluation of model responses in Polish, blind testing.
ToolsBenchmarks
Open PL LLM Leaderboard, MT-Bench PL, EQ-Bench PL — in one place.
ToolsData Dashboard
Transparency of the training corpus — derived from SpeakLeash / Spichlerz.
TrainingEskadra Bielika
Active network of contributors, testers, and model evaluators.
We don't just publish models. We show how they're built.
Bielik grew out of the SpeakLeash / Spichlerz community — a project aimed at creating, cataloguing, and documenting Polish datasets for large language models. Today we continue this tradition of open science: every model has a model card, technical publication, and benchmark results.
Join the Bielik Community
Bielik is a community-driven project. Join discussions, share ideas, and help shape the future of Polish-language AI.
Project news, partnerships, job openings and industry threads.
X
Quick updates, technical threads and discussions with the AI community.
Discord
Daily conversation, support, announcements and topic channels for developers.
Hugging Face
All model weights, collections, model cards and inference examples.
GitHub
Code, issues, PRs, evaluation tools and repositories across the whole ecosystem.
YouTube
Conference recordings, tutorials, webinars and model demos.
News, community posts and event coverage from the project.
Behind the scenes, visual result summaries and team life.
Getting started
The easiest way is Ollama: "ollama run SpeakLeash/bielik-11b-v3.0-instruct". Alternatively, download the model from Hugging Face and run it via llama.cpp, vLLM, or transformers. Detailed instructions are in the Models section.
License & availability
Yes. Model weights, model cards, evaluation tooling code, and technical publications are publicly available on Hugging Face and GitHub. The Apache 2.0 license allows commercial use without licensing fees.
Yes. The Apache 2.0 license permits commercial use, modifications, and redistribution. There are no licensing fees or deployment restrictions — on-premise, cloud, or edge.
Models
For most production use cases we recommend Bielik 11B v3.0 Instruct. For local testing and memory-constrained devices — Bielik 4.5B. For edge and IoT — Bielik 1.5B. For content moderation — Bielik Guard 0.5B.
Bielik 11B v3.0 and 4.5B v3.0 support a context window of 8,192 tokens. Bielik 1.5B v3.0 supports 4,096 tokens. The BPE tokenizer is optimized for Polish and encodes Polish text with fewer tokens than general-purpose tokenizers.
Base is a raw language model — it predicts the next token without special instructions. Instruct is fine-tuned (SFT + RLHF) for dialogue, following instructions, and assistant tasks. For production deployments, always use the Instruct version.
Other
Bielik is a family of open language models optimized for the Polish language — from compact 1.5B models to the flagship 11B. The project is developed by Speakleash Foundation and released under the Apache 2.0 license.
Bielik is developed by SpeakLeash Foundation together with strategic, scientific, and technology partners, as well as a broad contributor community. The project was founded in Poland and is led by Polish AI researchers.
Get in touch
Write to the right address. We reply by e-mail.