whatmodel.sh / Gemma 2 9B IT DPO (Princeton)

Gemma 2 9B IT DPO (Princeton)

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

Gemma 2 9B IT DPO (Princeton) is an open-weights language model from Princeton NLP, released July 2024. Its published size is 9.24B parameters.

Catalogue identity notes

Maker repo princeton-nlp/gemma-2-9b-it-DPO @f646c99: no licence tag on the card. 9,241,705,984 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-07: month the maker's Hugging Face repo was created (createdAt 2024-07-16).

59.1±1.4#206 of 719 LLMsfrom 3 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Gemma 2 9B IT DPO (Princeton), out of 828 with a score, then more from Princeton NLP.

#modelscorewhereRAMreleased
246DeepSeek V3 (Dec '24) DeepSeek59±1api $0.46/M +local~337GB2024-12
247Gemma 2 9B IT SimPO Princeton NLP59±1local~7.6GB2024-07
248Gemma 2 9B IT DPO (Princeton) Princeton NLP59±1local~7.6GB2024-07
249Trinity-Large-Preview Arcee AI59±2local~155GB2026-01
250GLM-4.7-Flash Z.ai59±1api $0.0000/M +local~19GB2026-01
more from Princeton NLP
400Llama-3-Instruct-8B-SimPO Princeton NLP51±1local~6.6GB2024-05
408Llama-3-8B-ProLong-512k-Instruct Princeton NLP50±5local~35GB2024-08
647Llama-3-Instruct-8B-SimPO-v0.2 Princeton NLP39±1local~6.6GB2024-07

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #136 of 393 * · 76% of its score · 1 test

Beats o3-mini, EXAONE 4.5 33B, INTELLECT-3 here, though they rank higher overall. Trails LFM2.5 8B-A1B, LFM2.5 2.6B, Spark-X2.5 1.7B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled67.7% ✎▁▂▂▃▆▆█▆▄▄▃▁ beats 119/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%at its level
other tests2 not in a task · 24% of its score
testresultvs the others in its rundifficultycountswhy
WildBench v2 WB-Score (task macro)53.2230 WB-Score ✎▁·▁▁·▃█▄▇▆▅▆ beats 43/52avg 45.199 WB-Score▇▇▇▇▇▇▇▇ 21%sharp
Open PT-LLM Leaderboard average (9 Portuguese tasks)70.4% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 167/276medium · avg 73%▇ 3.0%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 Gemma 2 9B IT DPO (Princeton) · needs ~5.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/gemma-2-9b-it-DPO-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/gemma-2-9b-it-DPO-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 Gemma 2 9B IT DPO (Princeton) · needs ~5.8 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/gemma-2-9b-it-DPO-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 Gemma 2 9B IT DPO (Princeton) · needs ~5.8 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/gemma-2-9b-it-DPO-GGUF:Q4_K_M

Other ways to run it

  1. Run it as published · needs ~18.48 GB · from huggingface.co/princeton-nlp (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='princeton-nlp/gemma-2-9b-it-DPO', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/princeton-nlp ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 76%, WildBench v2 leaderboard data… 21%, Open Portuguese LLM Leaderboa… 3%

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
AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 76%Apache-2.0
WildBench v2 leaderboard data (Ai2)1▇▇▇▇▇▇ 21%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 3%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 59.1

$ 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