basal-2.0-4.5B
Decisions and classification on a small GPU
Bielik, PLLuM and basal: open-weight models trained on Polish that run on your own server.
At a glance
Each family has a different job. Bielik and PLLuM chat and write, basal makes decisions, and Qra is a base for fine-tuning.
| Family | Built by | Sizes | License | Best for |
|---|---|---|---|---|
| Bielik | SpeakLeash and ACK Cyfronet AGH | 1.5B, 4.5B, 7B, 11B plus Bielik Guard 0.1B and 0.5B | Apache 2.0 | Chat, RAG, Polish writing, content moderation |
| PLLuM | PLLuM consortium, since 2025 HIVE AI, with the Ministry of Digital Affairs | 4B, 8B, 12B, 8x7B, 70B | Apache 2.0; Llama-based versions: Llama 3.1 | Chat, instructions, summaries, public-sector Polish |
| basal | Remigiusz Kinas | 0.8B to 31B, built on Bielik v3 and Gemma 4 | Apache 2.0 | Decisions: choice, yes/no, score with calibration |
| Qra | OPI PIB and Gdańsk University of Technology | 1B, 7B, 13B (base models) | Apache 2.0, Llama 2 | Base for fine-tuning on your own data |
Search for a model and filter by release date, memory or family. We show the newest and the most downloaded release of each model. Last update: November 2026.
No models match these filters.
18 models
| Model | Best for | Released on HF | License | Links |
|---|---|---|---|---|
| basal-2.0-4.5B License Apache 2.0 | Decisions and classification on a small GPU | Apache 2.0 | ||
| basal-2.0-mini License Apache 2.0 | Fastest yes/no and choice decisions | Apache 2.0 | ||
| basal-omni-1.0-mini License Apache 2.0 | Decisions on one 8 GB-class GPU | Apache 2.0 | ||
| basal-omni-2.0-mini-preview License Apache 2.0 | basal 2.0 preview: bidirectional decisions | Apache 2.0 | ||
| basal-omni-pico License Apache 2.0 | Smallest decision model, CPU-friendly | Apache 2.0 | ||
| Bielik-1.5B-v3.0-Instruct License Apache 2.0 | Smallest Bielik for simple tasks and edge devices | Apache 2.0 | ||
| Bielik-4.5B-v3.0-Instruct License Apache 2.0 | Small Bielik for laptops: chat and simple tasks | Apache 2.0 | ||
| Bielik-Guard-0.1B-v1.1 License Apache 2.0 | Lightest Polish content moderation | Apache 2.0 | ||
| Bielik-Guard-0.5B-v1.1 License Apache 2.0 | Polish harmful-content detection | Apache 2.0 | ||
| Bielik-Minitron-7B-v3.0-Instruct License Apache 2.0 | Lighter 7B Bielik pruned from 11B | Apache 2.0 | ||
| Bielik-PL-Minitron-7B-v3.0-Instruct License Apache 2.0 | Lighter 7B Bielik with a Polish tokenizer | Apache 2.0 | ||
| Llama-PLLuM-8B-chat-2412 License Llama 3.1 | PLLuM 8B chat (first release) | Llama 3.1 | ||
| Llama-PLLuM-8B-chat-2512 License Llama 3.1 | PLLuM chat built on Llama 3.1 8B | Llama 3.1 | ||
| Llama-PLLuM-8B-instruct-2512 License Llama 3.1 | PLLuM built on Llama 3.1 8B | Llama 3.1 | ||
| PLLuM-4B-chat-2512 License Apache 2.0 | Light Polish chat | Apache 2.0 | ||
| PLLuM-4B-instruct-2512 License Apache 2.0 | Light PLLuM for simple instructions | Apache 2.0 | ||
| Qra-1b License Apache 2.0 | Small base for experiments | Apache 2.0 | ||
| Qra-7b License Llama 2 | 7B base for your own fine-tuning | Llama 2 |
Decisions and classification on a small GPU
Fastest yes/no and choice decisions
Decisions on one 8 GB-class GPU
basal 2.0 preview: bidirectional decisions
Smallest decision model, CPU-friendly
Smallest Bielik for simple tasks and edge devices
Small Bielik for laptops: chat and simple tasks
Lightest Polish content moderation
Polish harmful-content detection
Lighter 7B Bielik pruned from 11B
Lighter 7B Bielik with a Polish tokenizer
PLLuM 8B chat (first release)
PLLuM chat built on Llama 3.1 8B
PLLuM built on Llama 3.1 8B
Light Polish chat
Light PLLuM for simple instructions
Small base for experiments
7B base for your own fine-tuning
10 models
| Model | Best for | Released on HF | License | Links |
|---|---|---|---|---|
| basal-2.0-max License Apache 2.0 | Most accurate basal: routing, rules, scores | Apache 2.0 | ||
| basal-omni-1.0-max License Apache 2.0 | Decisions and scores on Gemma 4 12B | Apache 2.0 | ||
| basal-omni-1.1-max License Apache 2.0 | Decisions over long documents and data | Apache 2.0 | ||
| Bielik-11B-v3.0-Instruct License Apache 2.0 | Most downloaded Polish model: chat and RAG | Apache 2.0 | ||
| Bielik-11B-v3.1-Instruct License Apache 2.0 | Latest Bielik: Polish chat, tool use and reasoning | Apache 2.0 | ||
| Bielik-PL-11B-v3.0-Instruct License Apache 2.0 | Bielik 11B with a Polish-optimised tokenizer | Apache 2.0 | ||
| PLLuM-12B-chat-2412 License Apache 2.0 | Polish chat (first release) | Apache 2.0 | ||
| PLLuM-12B-chat-2512 License Apache 2.0 | Polish chat assistant | Apache 2.0 | ||
| PLLuM-12B-instruct-2512 License Apache 2.0 | Polish instructions, summaries and Q&A | Apache 2.0 | ||
| Qra-13b License Llama 2 | Base for fine-tuning on Polish data | Llama 2 |
Most accurate basal: routing, rules, scores
Decisions and scores on Gemma 4 12B
Decisions over long documents and data
Most downloaded Polish model: chat and RAG
Latest Bielik: Polish chat, tool use and reasoning
Bielik 11B with a Polish-optimised tokenizer
Polish chat (first release)
Polish chat assistant
Polish instructions, summaries and Q&A
Base for fine-tuning on Polish data
1 model
| Model | Best for | Released on HF | License | Links |
|---|---|---|---|---|
| basal-omni-1.0-ultra License Apache 2.0 | Strongest basal-omni for hard decisions | Apache 2.0 |
Strongest basal-omni for hard decisions
2 models
| Model | Best for | Released on HF | License | Links |
|---|---|---|---|---|
| PLLuM-8x7B-chat-2412 License Apache 2.0 | PLLuM MoE chat | Apache 2.0 | ||
| PLLuM-8x7B-instruct-2412 License Apache 2.0 | PLLuM MoE for instructions and summaries | Apache 2.0 |
PLLuM MoE chat
PLLuM MoE for instructions and summaries
2 models
| Model | Best for | Released on HF | License | Links |
|---|---|---|---|---|
| Llama-PLLuM-70B-chat-2512 License Llama 3.1 | Largest PLLuM chat model | Llama 3.1 | ||
| Llama-PLLuM-70B-instruct-2512 License Llama 3.1 | Largest PLLuM for harder tasks | Llama 3.1 |
Largest PLLuM chat model
Largest PLLuM for harder tasks
New
basal does not chat. It reads a message, a document or a log and answers a question from a closed list of answers: a choice, yes/no or a score. It returns a probability for each answer, so you know when a decision can be automated and when it should go to a person.
basal-2.0 is built on Bielik v3 (1.5B, 4.5B, 11B). basal-omni is built on Gemma 4 (8B to 31B), and basal-omni-pico (0.8B) on Qwen3.5 and also runs on a CPU. On 14 November 2026 the author released basal-omni-2.0-mini (preview) with bidirectional reading. The full 2.0 family will follow later.
When it makes sense
Comparison
Global open-source models handle Polish well too, and the largest ones are stronger at reasoning and coding. Polish models win where natural Polish text, Polish context and a small size matter.
There is no single answer for every company. The best approach is to compare two or three models on your own data, for example Bielik 11B with a model from the same RAM tier in the best local LLMs table.
Hardware
Where the model memory lives depends on your hardware. All tiers in the table assume Q4_K_M quantization.
| Hardware | What to check | Example with Polish models |
|---|---|---|
| Mac (M1–M5) | Total RAM. CPU and GPU share one memory pool, so no separate GPU is needed. | A Mac with 16 GB RAM runs Bielik 11B or PLLuM 12B. |
| PC with NVIDIA GPU | GPU VRAM. The model must fit in the GPU’s memory. System RAM alone is not enough. | An 8 GB card (e.g. RTX 4060) is enough for Bielik 4.5B. Bielik 11B needs a 16 GB card (e.g. RTX 5070 Ti). |
| Multi-GPU server | Combined VRAM. Large models split across GPUs. | Llama-PLLuM-70B needs about 48–64 GB: two RTX 5090 cards (2 × 32 GB) or one H100 80 GB. |
| CPU only | System RAM. Slower than a GPU, but small models are usable. | basal-omni-pico (0.8B) and Bielik 1.5B run even on an ordinary laptop. |
Generation speed depends on hardware and text length, so we do not list it. We explain more in the local LLM ranking.
Step by step
FAQ
Yes. Current Bielik models are Apache 2.0, which allows commercial use. The table only lists models whose licenses allow commercial use.
About 16 GB of RAM or VRAM with Q4_K_M quantization. Bielik 4.5B fits in 8 GB.
Bielik is developed by the SpeakLeash community with ACK Cyfronet AGH. PLLuM comes from a consortium of research institutions with the Ministry of Digital Affairs and leans more towards official and public-sector Polish.
Not for every task. Large cloud models are stronger at reasoning. A Polish model wins when data must stay in your company and the task needs good Polish.
No. basal is a decision model: it picks an answer from the list you give it and returns its probability. It does not write longer texts.
Every month we pull new releases of Bielik, PLLuM, basal and Qra from Hugging Face. Last update: November 2026.
Describe the task and the data. We will advise which model to pick, what hardware to run it on and how to connect it to your systems.
Reply within one business day. No sales call needed.
The form did not load (an ad blocker may be blocking it). Write to us at sales@droptica.com