whatmodel.sh / Llama-PLLuM-70B-instruct (2412)

Llama-PLLuM-70B-instruct (2412)

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

Llama-PLLuM-70B-instruct (2412) is an open-weights language model from PLLuM consortium (CYFRAGOVPL), released February 2025. Its published size is 70.55B parameters. Licence: llama3.1.

Catalogue identity notes

Maker repo CYFRAGOVPL/Llama-PLLuM-70B-instruct-2412 @2e5e4b4 (requested as CYFRAGOVPL/Llama-PLLuM-70B-instruct, which the HF API redirects to CYFRAGOVPL/Llama-PLLuM-70B-instruct-2412): licence tag llama3.1. 70,553,739,264 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-02: month the maker's Hugging Face repo was created (createdAt 2025-02-06).

53.2±2.9#364 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 Llama-PLLuM-70B-instruct (2412), out of 1132 with a score, then more from PLLuM consortium (CYFRAGOVPL).

#modelscorewhereRAMreleased
472Qwen2-VL 72B Instruct Alibaba53±1local~34GB2024-09
473Bielik 11B v2.5 Instruct SpeakLeash53±3local~8.5GB2025-05
474Llama-PLLuM-70B-instruct (2412) PLLuM consortium (CYFRAGOVPL)53±3local~29GB2025-02
475Gemini 1.5 Flash Experimental (0827) Google53±1comparison only2024-08
476GPT-4o mini (2024-07-18) OpenAI53±0api $0.26/M2024-07
more from PLLuM consortium (CYFRAGOVPL)
423PLLuM-12B-nc-chat (2507) PLLuM consortium (CYFRAGOVPL)55±4local~27GB2025-07
484Llama-PLLuM-70B-chat (2412) PLLuM consortium (CYFRAGOVPL)53±4local~29GB2025-02
561PLLuM-12B-nc-instruct (2507) PLLuM consortium (CYFRAGOVPL)50±4local~27GB2025-07

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
Polish medical board exams, bias-mitigated MCQ protocol (7-exam average)57.1% ✎▄·▂▂▂··█▂▄·▄ beats 7/13hard · avg 48%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%at its level
CPTUB average (SpeakLeash, 0-5 judge scale)66.5% ✎▁▂▂▂▃█▃▆▅▄▂▃ beats 48/95easy · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%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 Llama-PLLuM-70B-instruct (2412) · needs ~42.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Llama-PLLuM-70B-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/Llama-PLLuM-70B-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 Llama-PLLuM-70B-instruct (2412) · needs ~42.5 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Llama-PLLuM-70B-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 Llama-PLLuM-70B-instruct (2412) · needs ~42.5 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Llama-PLLuM-70B-instruct-2412-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~141.11 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/Llama-PLLuM-70B-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 · Reassessing High-Performing L… 50%, SpeakLeash CPTUB (Complex Pol… 46%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 50%CC BY-SA 4.0
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 46%MIT
prior · pull toward the middle▇ 4%
weighted average= 53.2

$ 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