whatmodel.sh / Gemma-2-9B-It-SPPO-Iter3

Gemma-2-9B-It-SPPO-Iter3

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

Gemma-2-9B-It-SPPO-Iter3 is an open-weights language model from UCLA AGI (SPPO), released June 2024. Its published size is 9.24B parameters. Licence: gemma.

Catalogue identity notes

Maker repo UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3 @2261f2a: licence tag gemma. 9,241,705,984 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2024-06: month the maker's Hugging Face repo was created (createdAt 2024-06-29).

55.5±1.5#303 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 Gemma-2-9B-It-SPPO-Iter3, out of 1132 with a score, then more from UCLA AGI (SPPO).

#modelscorewhereRAMreleased
400Magistral Medium 1.0 (2506) Mistral56±1comparison only2025-06
401Llama3-Instruct-8B-WPO-HB-v2 wzhouad (WPO)56±2local~35GB2024-07
402Gemma-2-9B-It-SPPO-Iter3 UCLA AGI (SPPO)56±2local~7GB2024-06
403GPT-4 Turbo (2024-04-09) OpenAI55±0api $15.00/M2024-04
404Yi-Lightning 01.AI55±1api price unknown2024-10
more from UCLA AGI (SPPO)
577Llama-3-Instruct-8B-SPPO-Iter3 UCLA AGI (SPPO)50±2local~6.6GB2024-06
681Mistral7B-PairRM-SPPO UCLA AGI (SPPO)47±2local~6.1GB2024-05

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #208 of 466 * · 95% of its score · 1 test

Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
AlpacaEval 2 length-controlled54.0% ✎▁▂▂▃▆▆█▆▄▄▁▁ beats 112/122medium · avg 39%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%at its level
other tests1 not in a task · 4.0% of its score
testresultvs the others in its rundifficultycountswhy
Open PT-LLM Leaderboard average (9 Portuguese tasks)74.3% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 215/276medium · avg 73%▇▇ 4.0%at its level · 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-SPPO-Iter3 · needs ~5.8 GB · from huggingface.co/bartowski
    chat in the terminal
    llama cli -hf bartowski/Gemma-2-9B-It-SPPO-Iter3-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf bartowski/Gemma-2-9B-It-SPPO-Iter3-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-SPPO-Iter3 · needs ~5.8 GB · from huggingface.co/bartowski

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/bartowski/Gemma-2-9B-It-SPPO-Iter3-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-SPPO-Iter3 · needs ~5.8 GB · from huggingface.co/bartowski
    chat in the terminal
    ollama run hf.co/bartowski/Gemma-2-9B-It-SPPO-Iter3-GGUF:Q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run Gemma-2-9B-It-SPPO-Iter3 · needs ~5.2 GB, Mac only · from huggingface.co/mlx-community
    chat in the terminal
    mlx_lm.chat --model mlx-community/Gemma-2-9B-It-SPPO-Iter3-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mlx-community/Gemma-2-9B-It-SPPO-Iter3-4bit

Other ways to run it

  1. Run it as published · needs ~18.48 GB · from huggingface.co/UCLA-AGI (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/UCLA-AGI ↗

$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 95%, Open Portuguese LLM Leaderboa… 4%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%Apache-2.0
Open Portuguese LLM Leaderboard (archived)1▇ 4%Apache-2.0
prior · pull toward the middle▇ 1%
weighted average= 55.5

$ 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