← All models

Made by Google · License: Gemma Terms of Use

Model

Gemma 2 9B

A free model for chat. You start it with one command.

Not sure which model? Start from your computer.

Start it

  1. Install Ollama from ollama.com/download.
  2. Open Terminal.
  3. Paste this command:
ollama run gemma2:9b

Copied word for word from its source.

What happens next

Will it run on my computer?

Mac

16 GBFits24 GBFits32 GBFits36 GBFits48 GBFits64 GBFits96 GBFits128 GBFits192 GBFits256 GBFits512 GBFits

NVIDIA graphics card

8 GBTight12 GBFits16 GBFits24 GBFits32 GBFitsTwo 24 GB cardsFits

AMD Ryzen AI Max

64 GBFits128 GBFits

This is our estimate from the download size. A tested run on a computer overrides it. “Smaller version” means a smaller download than the command below. Tap your computer to see the exact command.

If it breaks

  1. It forgets the start of a long chat, or ignores most of a document you pasted.

    Ollama may not use the model's full context length by default. When a chat runs past that, the oldest messages are dropped without any warning.

    Raise the context length with the slider in the Ollama app's Settings. Ollama's FAQ shows a chat command for this. Its example number, 4,096 tokens, is too small for long chats, so do not copy it. A longer context uses more memory. Check the CONTEXT column of ollama ps after.

    Source: 1 · 2 · 3

  2. Replies crawl out a word at a time.

    The model did not fit in graphics memory, so Ollama quietly ran part of it on the CPU. Speed drops a lot, but you get no error.

    Run ollama ps while the model runs. Look at the PROCESSOR column. If it does not say 100% GPU, free some memory. Close other models (Ollama's command list shows how), lower the context length, or pick a smaller version.

    ollama ps

    Copied word for word from its source.

    Source: 1 · 2 · 3

More help: Ollama's help page.

Sizes and versions

Will it run on my computer?

For gemma2:9b (5.4 GB download; Same file as the counted tests, checked 2026-10-20). Context up to 8K, but Ollama may start lower, see below.

8 GB graphics cardTight
16 GB graphics cardFits
24 GB graphics cardFits
32 GB graphics cardFits
16 GB MacFits
24 GB MacFits
32 GB MacFits
64 GB+ MacFits
AMD Ryzen AI Max+ PC, 128 GB (graphics memory set to 96 GB)Fits
  • Fit is our estimate from published download sizes. A tested run overrides it.
  • Fits = download x 1.25 + 2 GB fits in usable memory. That leaves room for longer chats.
  • Tight = only download + 1.5 GB fits. Short chats work, but long chats or documents may spill onto the CPU and slow down.
  • Usable memory on a graphics card is all of its graphics memory.
  • On a Mac it is 2/3 of memory up to 32 GB and 3/4 at 64 GB+. By default macOS keeps part of memory away from the GPU. Apple says a 32 GB Mac gives the GPU 21 GB and a 64 GB Mac 48 GB.
  • On an AMD Ryzen AI Max+ PC with 128 GB, it is the graphics memory you set in AMD Software. AMD says you can set up to 96 GB.
  • Apple · AMD

Sizes checked 2026-10-20.

START HERE Easy: Ollama

INSTALLOllama. ollama.com/download
RUN
ollama run gemma2:9b

Copied word for word from its source.

SIZE5.4 GB download
NEEDSA 12 GB graphics card or more. An 8 GB card is tight.
NOTEIts context window is 8K tokens (Ollama's page).
SOURCEsource · checked 2026-10-20

Recommended quants

  • Ollama gemma2:9b (5.4 GB)
    ollama gemma2
    Ollama tag named by the counted test.
Scores and how it compares

Independent score: none found yet (checked 2026-10-20). Artificial Analysis lists no Intelligence Index for this model on the pages we read (Oct 20, 2026).

Arena (ranks our computer pages):

Checked 2026-10-19.

Pick this if you have a 12, 16 or 24 GB graphics card and want chat or writing help.

Skip this if you need coding, documents or images help. It has no counted score for those jobs on our pages. Its context window is 8K tokens.

Compare: Phi-4 (14B) · Pick your computer

Picked onJust make it work: NVIDIA 12, 16, 24 GB (at least one job)
Settings and apps

Chat template Works

Ollama's tag carries the chat template.

Fix:

Sampling settings

Runtimes

OllamaWorksOfficial library tag gemma2:9b.
Sources
MADE BYGoogle
LICENSEGemma Terms of Use · model page · checked 2026-10-20
RELEASED2024-06-27
CHECKED2026-10-20 · 2 sources

A 9B model from Google. One Ollama command (about 5.4 GB). It fits a 12 GB graphics card.

Known issues

    Sources checked

    Spotted something wrong or a new fix? Email corrections to hello@runcards.dev. Corrections are reviewed before publishing.

    Details

    Words used here

    • Arena (LMArena) is a public leaderboard. People compare two answers and vote for the better one. WebDev, Coding and Writing are some of its boards.
    • B after a number means billion weights (parameters). A model with more weights needs more memory. T means trillion.
    • Chat template (often a Jinja template) tells the program how to lay out the chat for the model.
    • Context (also called the window) is how much text the model can keep in mind at one time. It is counted in tokens.
    • CPU is the main chip of the computer. A model that runs on the CPU is much slower than on the GPU.
    • GPU is the graphics chip. AI models run on it. On a Mac, the GPU is part of the main chip.
    • K after a token count means thousand, and M means million. 32K is about 32,000 tokens.
    • Quant (quantized version) is a smaller copy of a model. It keeps each number in fewer bits. It uses less memory and can lose a little quality.
    • Tag is the part after the colon in a model name, such as gemma4:26b. It picks one size or version.

    Checked Oct 20, 2026. Some staleness is always possible: versions and links change. RunCards is not affiliated with any model maker, recipe author or repo. Troubleshooting belongs to each repo or author. Read more

    Did you find a mistake? Suggest a fix. See what we changed.