whatmodel.sh / PLLuM-12B-instruct (2412)

PLLuM-12B-instruct (2412)

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

PLLuM-12B-instruct (2412) is an open-weights language model from PLLuM consortium (CYFRAGOVPL), released February 2025. Its published size is 12.25B parameters. Licence: apache-2.0.

Catalogue identity notes

Maker repo CYFRAGOVPL/PLLuM-12B-instruct-2412 @a123ff5 (requested as CYFRAGOVPL/PLLuM-12B-instruct, which the HF API redirects to CYFRAGOVPL/PLLuM-12B-instruct-2412): licence tag apache-2.0. 12,247,782,400 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-02: month the maker's Hugging Face repo was created (createdAt 2025-02-07).

44.9±2.9#590 of 949 LLMsfrom 2 benchmark results across 2 sources* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of PLLuM-12B-instruct (2412), out of 1132 with a score, then more from PLLuM consortium (CYFRAGOVPL).

#modelscorewhereRAMreleased
742Zephyr ORPO 141B-A35B v0.1 Hugging Face45±2local~56GB2024-04
743Phi-3-medium-4k-instruct Microsoft45±1local~9.8GB2024-05
744PLLuM-12B-instruct (2412) PLLuM consortium (CYFRAGOVPL)45±3local~9.4GB2025-02
745Qwen2-Math 1.5B Instruct Alibaba45±2local~2.4GB2024-08
746Mistral Small (2402) Mistral45±1comparison only2024-02
more from PLLuM consortium (CYFRAGOVPL)
423PLLuM-12B-nc-chat (2507) PLLuM consortium (CYFRAGOVPL)55±4local~27GB2025-07
474Llama-PLLuM-70B-instruct (2412) PLLuM consortium (CYFRAGOVPL)53±3local~29GB2025-02
484Llama-PLLuM-70B-chat (2412) PLLuM consortium (CYFRAGOVPL)53±4local~29GB2025-02

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 96% of its score
testresultvs the others in its rundifficultycountswhy
CPTUB average (SpeakLeash, 0-5 judge scale)61.9% ✎▁▂▂▂▃█▃▆▅▄▂▃ beats 37/95easy · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 55%at its level
Polish medical board exams, bias-mitigated MCQ protocol (7-exam average)35.9% ✎▄·▃▂▂··█▂▄·▄ beats 2/13hard · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 41%at its level

$ 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 PLLuM-12B-instruct (2412) · needs ~7.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/PLLuM-12B-instruct-2412-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/PLLuM-12B-instruct-2412-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 PLLuM-12B-instruct (2412) · needs ~7.5 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/PLLuM-12B-instruct-2412-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 PLLuM-12B-instruct (2412) · needs ~7.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/PLLuM-12B-instruct-2412-GGUF:Q4_K_M

MLX (Mac)

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run PLLuM-12B-instruct (2412) · needs ~10 GB, Mac only · from huggingface.co/lukagra
    chat in the terminal
    mlx_lm.chat --model lukagra/PLLuM-12B-instruct-Q6-mlx
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lukagra/PLLuM-12B-instruct-Q6-mlx

Other ways to run it

  1. Run it as published · needs ~24.5 GB · from huggingface.co/CYFRAGOVPL
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='CYFRAGOVPL/PLLuM-12B-instruct-2412', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Weights and documentation: huggingface.co/CYFRAGOVPL ↗

$ how the score was worked out · SpeakLeash CPTUB (Complex Pol… 55%, Reassessing High-Performing L… 41%

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
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 55%MIT
Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance? (arXiv:2606.12250v1)1▇▇▇▇▇▇▇▇▇▇▇▇ 41%CC BY-SA 4.0
prior · pull toward the middle▇ 4%
weighted average= 44.9

$ 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