whatmodel.sh / Gemma 3 270M IT

Gemma 3 270M IT

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

Gemma 3 270M IT is an open-weights language model from Google, released August 2025. Its published size is 0.27B parameters and a 32k-token context window. Licence: gemma.

14.7±3.7#699 of 719 LLMsfrom 5 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Gemma 3 270M IT, out of 828 with a score, then more from Google.

#modelscorewhereRAMreleased
805Dolly v2 12B Databricks17±2comparison only2023-04
806OPT-1.3B Meta16±1local~4.3GB2022-05
807Gemma 3 270M IT Google15±4local~1.7GB2025-08
808Pythia 1B EleutherAI14±1local~2.2GB2023-02
809StableLM-Tuned-Alpha 7B Stability AI14±2local~6.9GB2023-04
more from Google
9Gemini 4 Argon (limited preview) Google82±1limited preview2026-09
23Gemini 3.8 Flash Google77±1api $1.50/M2026-09
32Gemini 3.7 Flash Google76±1api $1.50/M2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #340 of 393 * · 40% of its score · 1 test

Beats Gemma 4 E2B, Code Llama 70B Instruct, QwQ-32B-Preview here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
IFEval (aggregation unspecified) lab51.2% ✎▁▁▃▁▂▄▄▆█▃▂▁ beats 11/141very easy · avg 87%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 40%at its level
other tests8 not in a task · 54% of its score
testresultvs the others in its rundifficultycountswhy
BIG-Bench Hard lab26.7% ✎▁▃▁▁▂▄▅▅█▃▄▁ beats 1/129easy · avg 81%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%sharp · too hard for it
EuroEval Life in the UK (English knowledge MC), test split, 5-shot, accuracy26.7% ✎▁▁▃▁▁▁▁▂▄█▄▃ beats 4/146easy · avg 83%▇▇▇ 8.6%noisy
Open PT-LLM Leaderboard average (9 Portuguese tasks)28.2% ✎▃▁▁▁▁▁▁▁▂█▅▁ beats 37/276medium · avg 73%▇▇▇ 7.8%too hard for it · noisy
EuroEval HellaSwag (English), test split, 5-shot generative MC, accuracy25.2% ✎▃·▁▁▂▁▂▅█▇▄▁ beats 1/100medium · avg 68%▇ 2.8%too hard for it · noisy
ARC Challenge lab28.2% ✎▆▁▁▃▂▅▇█▄▃▃▂ beats 20/97easy · avg 85%—not counted yet: no other model in the same run to compare it with
WinoGrande lab52.3% ✎▁···▃▁▁▅█▇▃▁ beats 4/87easy · avg 89%—not counted yet: no other model in the same run to compare it with
HellaSwag lab37.7% ✎▁▁▁▃▂▂▃▇█▆▅▃ beats 3/85very easy · avg 92%—not counted yet: no other model in the same run to compare it with
PIQA lab66.2% ✎▁▁▁▃▃▄▇█▄▃▁▁ beats 6/83easy · avg 88%—not counted yet: no other model in the same run to compare it with

$ 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 3 270M IT · needs ~0.3 GB · from huggingface.co/lmstudio-community
    chat in the terminal
    llama cli -hf lmstudio-community/gemma-3-270m-it-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf lmstudio-community/gemma-3-270m-it-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 3 270M IT · needs ~0.3 GB · from huggingface.co/lmstudio-community

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/lmstudio-community/gemma-3-270m-it-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 3 270M IT · needs ~0.82 GB · from ollama.com
    chat in the terminal
    ollama run gemma3:270m

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 3 270M IT · needs ~0.2 GB, Mac only · from huggingface.co/lmstudio-community
    chat in the terminal
    mlx_lm.chat --model lmstudio-community/gemma-3-270m-it-MLX-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model lmstudio-community/gemma-3-270m-it-MLX-4bit

Official weights and documentation: huggingface.co/google ↗

$ how the score was worked out · Google DeepMind Gemma 3 270M… 75%, EuroEval leaderboards (result… 11%, Open Portuguese LLM Leaderboa… 8%

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
Google DeepMind Gemma 3 270M IT model card · lab-reported2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 75%CC-BY-4.0
EuroEval leaderboards (results collection), English generative leaderboard2▇▇▇ 11%MIT
Open Portuguese LLM Leaderboard (archived)1▇▇ 8%Apache-2.0
prior · pull toward the middle▇▇ 6%
weighted average= 14.7

not counted (4)

Google DeepMind Gemma 3 270M IT model cardHellaSwag [correct]37.7%fewer than three models have this test yet, or this source ran it for this model alone
Google DeepMind Gemma 3 270M IT model cardPIQA [correct]66.2%fewer than three models have this test yet, or this source ran it for this model alone
Google DeepMind Gemma 3 270M IT model cardARC Challenge [correct]28.2%fewer than three models have this test yet, or this source ran it for this model alone
Google DeepMind Gemma 3 270M IT model cardWinoGrande [correct]52.3%fewer than three models have this test yet, or this source ran it for this model alone

$ 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