Written by Jakub Rusinowski · Last updated September 19, 2026
Model library → Bielik → Bielik PL 11B v3.0 Instruct
11B instruct model trained across 32 European languages with Polish cherry-picked and processed by hand. The APT4 tokenizer encodes Polish in fewer tokens than a general vocabulary, so a given context window holds more Polish text. Fits a 12 GB card at Q4.
Bielik PL 11B v3.0 Instruct needs about 7 GB of VRAM at Q4_K_M — quantized weights plus framework overhead, before any KV cache. On Apple Silicon that figure comes out of unified memory.
| Parameters | 11 Billion |
| Context window | 32,768 |
| Architecture | Dense |
| Provider | SpeakLeash / ACK Cyfronet AGH |
| Licence | Apache 2.0 |
| Specified at | Q4_K_M |
| System RAM | 16 GB |
| Record updated | 2026-09-19 |
Corroborated — Two or more independent sources agree on these figures, but the model card itself was not retrieved. Treat the numbers as good rather than confirmed. Still unconfirmed: license, context, releaseDate.
Apache-2.0 — commercial use permitted. Commercial use permitted. No usage restrictions beyond attribution.
Modelled on a reference NVIDIA RTX 4090 (24 GB). Weights plus framework overhead only — this model publishes no architecture we can read, so no KV cache is included. A real session needs more; the figure is a floor, not a target. Speed figures are ESTIMATES from the memory-bandwidth roofline described on the methodology page, not benchmarks we ran — rows marked measured come from published or reader-submitted runs. VRAM here includes the KV cache, so it reads higher than the headline figure above, which does not.
| Quant | Bits/weight | Weights | VRAM needed | Est. speed | Fit on 24 GB |
|---|---|---|---|---|---|
| Q2_K | 2.63 | 3.6 GB | 4.4 GB | ~127 tok/s (est.) | Fits comfortably |
| Q3_K_M | 3.41 | 4.7 GB | 5.5 GB | ~108 tok/s (est.) | Fits comfortably |
| Q4_K_M | 4.83 | 6.6 GB | 7.4 GB | ~84 tok/s (est.) | Fits comfortably |
| Q5_K_M | 5.67 | 7.8 GB | 8.6 GB | ~75 tok/s (est.) | Fits comfortably |
| Q6_K | 6.56 | 9 GB | 9.8 GB | ~67 tok/s (est.) | Fits comfortably |
| Q8_0 | 8.50 | 11.7 GB | 12.5 GB | ~54 tok/s (est.) | Fits comfortably |
| F16 | 16.00 | 22 GB | 22.8 GB | ~31 tok/s (est.) | Tight fit |
Want to set your own context length and KV-cache quantization? Use the interactive VRAM calculator.
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
The cheapest catalogued GPU that runs Bielik PL 11B v3.0 Instruct is the Intel Arc B570 (10 GB).
Install Ollama, then run:
ollama run bielikWeights on Hugging Face: speakleash/Bielik-PL-11B-v3.0-Instruct.
Best for: polish, multilingual, chat, european languages.
← All Bielik models | VRAM calculator | Check your own hardware