whatmodel.sh / Bielik 11B v3.0 Instruct

Bielik 11B v3.0 Instruct

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Bielik 11B v3.0 Instruct is an open-weights language model from SpeakLeash, released November 2025. Its published size is 11.17B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo speakleash/Bielik-11B-v3.0-Instruct @735bfee: licence tag apache-2.0. 11,168,796,672 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-11: month the maker's Hugging Face repo was created (createdAt 2025-11-07). Gated repository (licence acceptance required on Hugging Face).

54.8±2.3#271 of 719 LLMsfrom 5 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of Bielik 11B v3.0 Instruct, out of 828 with a score, then more from SpeakLeash.

#modelscorewhereRAMreleased
323Qwen2.5 32B Instruct Alibaba55±1local~21GB2024-09
324Command A Reasoning (08-2025) Cohere55±2local~34GB
325Bielik 11B v3.0 Instruct SpeakLeash55±2local~8.1GB2025-11
326Olmo 3.1 32B Instruct Ai255±2local~21GB2025-12
327OpenThinker 32B Open Thoughts55±1local~21GB2025-02
more from SpeakLeash
338Bielik 11B v2.6 Instruct SpeakLeash54±3local~8.1GB2025-06
371Bielik 11B v2.1 Instruct SpeakLeash53±3local~8.5GB2024-08
379Bielik 11B v2.2 Instruct SpeakLeash52±3local~8.5GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests5 not in a task · 98% of its score
testresultvs the others in its rundifficultycountswhy
Polish medical board exams, bias-mitigated MCQ protocol (7-exam average)55.8% ✎▄·▂▂▂··█▂▄·▄ beats 6/13hard · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%at its level
CPTUB average (SpeakLeash, 0-5 judge scale) lab74.7% ✎▁▂▂▂▃█▃▆▅▄▂▃ beats 68/95easy · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇ 29%at its level
Polish EQ-Bench v2 (SpeakLeash) lab71.2% ✎▁··▁▁▂▂▆▅▆█▆ beats 57/70medium · avg 64%▇▇▇▇▇▇▇▇▇ 23%at its level
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy77.4% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 66/100medium · avg 68%▇▇▇ 7.5%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy82.7% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 80/146easy · avg 83%▇▇ 4.3%noisy

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run Bielik 11B v3.0 Instruct · needs ~6.7 GB · from huggingface.co/speakleash (official)
    chat in the terminal
    llama cli -hf speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run Bielik 11B v3.0 Instruct · needs ~6.7 GB · from huggingface.co/speakleash (official)

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/speakleash/Bielik-11B-v3.0-Instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run Bielik 11B v3.0 Instruct · needs ~6.7 GB · from huggingface.co/speakleash (official)
    chat in the terminal
    ollama run hf.co/speakleash/Bielik-11B-v3.0-Instruct-GGUF:Q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Bielik 11B v3.0 Instruct · needs ~6.3 GB, Mac only · from huggingface.co/speakleash (official)
    chat in the terminal
    mlx_lm.chat --model speakleash/Bielik-11B-v3.0-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model speakleash/Bielik-11B-v3.0-Instruct-MLX-4bit

Other ways to run it

  1. Run it as published · needs ~22.34 GB · from huggingface.co/speakleash (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='speakleash/Bielik-11B-v3.0-Instruct', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/speakleash ↗

$ how the score was worked out · Reassessing High-Performing L… 34%, SpeakLeash CPTUB (Complex Pol… 29%, SpeakLeash Polish EQ-Bench le… 23% and 1 more

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)1▇▇▇▇▇▇▇▇▇▇ 34%CC BY-SA 4.0
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark) · lab-reported1▇▇▇▇▇▇▇▇▇ 29%MIT
SpeakLeash Polish EQ-Bench leaderboard · lab-reported1▇▇▇▇▇▇▇ 23%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇▇▇ 12%MIT
prior · pull toward the middle▇ 2%
weighted average= 54.8

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json