whatmodel.sh / EuroLLM 9B Instruct

EuroLLM 9B Instruct

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

EuroLLM 9B Instruct is an open-weights language model from UTTER (EuroLLM), released November 2024. Its published size is 9.15B parameters and a 4k-token context window. Licence: apache-2.0.

Catalogue identity notes

utter-project/EuroLLM-9B-Instruct @f7ae2bc (created 2024-11-22, apache-2.0, gated: auto-approved access). EuroLLM 9B instruction model (Nov 2024 release, not the 2512 refresh). Independent rows: EuroEval English, Open PT-LLM, SpeakLeash CPTUB and Polish EQ-Bench.

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 9,152,319,488 parameters.

46.6±2.6#409 of 719 LLMsfrom 4 benchmark results across 4 sources

$ how it compares

The LLMs ranked either side of EuroLLM 9B Instruct, out of 828 with a score, then more from UTTER (EuroLLM).

#modelscorewhereRAMreleased
485CogVLM2 Llama3 Chinese Chat 19B Zhipu AI (THUDM)47±7comparison only2024-05
486InternLM2.5 7B Chat 1M Shanghai AI Laboratory (InternLM)47±4local~6.4GB2024-06
487EuroLLM 9B Instruct UTTER (EuroLLM)47±3local~6.9GB2024-11
488Granite 4.0 H Micro 3B IBM47±1local~3.4GB2025-09
489GPT-3.5 Turbo (0125) OpenAI46±1api $0.75/M2024-01
more from UTTER (EuroLLM)
767EuroLLM 1.7B Instruct UTTER (EuroLLM)27±3local~2.4GB2024-08

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests4 not in a task · 97% of its score
testresultvs the others in its rundifficultycountswhy
CPTUB average (SpeakLeash, 0-5 judge scale)62.9% ✎▁▂▂▂▃█▃▆▅▄▂▃ beats 40/95easy · avg 66%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%at its level
Polish EQ-Bench v2 (SpeakLeash)54.8% ✎▁··▁▁▂▂▆▅▆█▆ beats 30/70medium · avg 64%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 34%at its level
Open PT-LLM Leaderboard average (9 Portuguese tasks)68.3% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 150/276medium · avg 73%▇▇▇▇▇ 13%at its level · noisy
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy72.8% ✎▁▁▁▁▁▁▁▂▄█▄▃ beats 43/146easy · avg 83%▇▇▇ 7.6%at its level · noisy

$ where to run it

llama.cpp · recommended

  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 EuroLLM 9B Instruct · needs ~5.58 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/EuroLLM-9B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/EuroLLM-9B-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 EuroLLM 9B Instruct · needs ~5.58 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/EuroLLM-9B-Instruct-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run EuroLLM 9B Instruct · needs ~5.58 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/EuroLLM-9B-Instruct-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 EuroLLM 9B Instruct · needs ~5.1 GB, Mac only · from huggingface.co/stelterlab
    chat in the terminal
    mlx_lm.chat --model stelterlab/EuroLLM-9B-Instruct-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model stelterlab/EuroLLM-9B-Instruct-MLX-4bit

Other ways to run it

  1. Run it as published · needs ~18.3 GB, NVIDIA only · from huggingface.co/utter-project (official)
    vllm serve utter-project/EuroLLM-9B-Instruct

Official weights and documentation: huggingface.co/utter-project ↗

$ how the score was worked out · SpeakLeash CPTUB (Complex Pol… 42%, SpeakLeash Polish EQ-Bench le… 34%, Open Portuguese LLM Leaderboa… 13% 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
SpeakLeash CPTUB (Complex Polish Text Understanding Benchmark)1▇▇▇▇▇▇▇▇▇▇▇▇▇ 42%MIT
SpeakLeash Polish EQ-Bench leaderboard1▇▇▇▇▇▇▇▇▇▇ 34%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇▇▇▇ 13%Apache-2.0
EuroEval leaderboards (results collection), English generative leaderboard1▇▇ 8%MIT
prior · pull toward the middle▇ 3%
weighted average= 46.6

$ 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