whatmodel.sh / Fanar 1 9B Instruct

Fanar 1 9B Instruct

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

Fanar 1 9B Instruct is an open-weights language model from QCRI, released June 2025. Its published size is 8.78B parameters. Licence: apache-2.0.

Catalogue identity notes

QCRI/Fanar-1-9B-Instruct @d30938d (created 2025-06-01, licence apache-2.0). Qatar Computing Research Institute's Arabic-English model (Gemma-2 9B continual pretraining). Independent row: Inception AraGen-v3 (3C3H).

Model information sources

Release date ↗ · Weights licence ↗

HF safetensors metadata 8,783,871,488 parameters.

42.4±5.5#661 of 949 LLMsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Fanar 1 9B Instruct, out of 1132 with a score.

#modelscorewhereRAMreleased
818Aya Vision 32B Cohere42±3api price unknown +local~71GB2025-03
819Llama-3-Nanda-10B-Chat MBZUAI & Inception42±5local~43GB2024-10
820Fanar 1 9B Instruct QCRI42±6local~7.2GB2025-06
821Tulu 2 DPO 70B Ai242±1local~32GB2023-11
822Mathstral 7B v0.1 Mistral AI42±1local~5.8GB2024-07

see all LLMs · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 87% of its score
testresultvs the others in its rundifficultycountswhy
AraGen-v3 3C3H score (Inception, Claude Sonnet 4 judge)16.2% ✎▁▁·▁▂▂▄█▄▅▄▄ beats 13/66hard · avg 31%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 87%typical

$ 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 Fanar 1 9B Instruct · needs ~5.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/Fanar-1-9B-Instruct-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/Fanar-1-9B-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 Fanar 1 9B Instruct · needs ~5.4 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/Fanar-1-9B-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 Fanar 1 9B Instruct · needs ~5.4 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/Fanar-1-9B-Instruct-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~17.6 GB, NVIDIA only · from huggingface.co/QCRI (official)
    vllm serve QCRI/Fanar-1-9B-Instruct

Official weights and documentation: huggingface.co/QCRI ↗

$ how the score was worked out · Inception Arabic/Hindi leader… 87%

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
Inception Arabic/Hindi leaderboards (AraGen-v3, HindiGen-v1, Arabic IFEval)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 87%Apache-2.0
prior · pull toward the middle▇▇▇▇ 13%
weighted average= 42.4

$ 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