Can I run Gemma 2 27B locally?

Yes — the weights are open and hosted at google/gemma-2-27b-it on Hugging Face. At 27B parameters you will want around 24 GB of VRAM for comfortable local inference; tools like Ollama or LM Studio can handle it.

What does Gemma 2 27B cost via API?

Google prices it at $0.65 per million tokens for both input and output, which is on the affordable end for a model of this size. The context window is 8,192 tokens.

How does Gemma 2 27B differ from Gemini models?

Gemma 2 27B is built on the same research as Gemini but is an open-weights release you can download and self-host; Gemini models are closed and API-only. Gemma 2 27B is also considerably smaller than the top Gemini tiers.

Gemma 2 27B

3159°

#llm #google #reasoning #summarization #research #local

Runs on Graydient

Run this model

Offers / Ads

Easy Creator (Prism) Web

Unlimited · flat fee

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Unlimited · flat fee

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Pro studio (SpyGlass) Web

Unlimited · flat fee

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Unlimited · flat fee

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

Unlimited · flat fee

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Google | 8,192 token context | $0.65/M input, $0.65/M output. Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. See the launch announcementOpens in new tab for more details. Usage of Gemma is subject to Google's Gemma Terms of UseOpens in new tab.

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Gemma 2 27B is Google's open-weights 27-billion-parameter instruction-tuned model, built on the same research lineage as Gemini. It sits in a useful middle ground: large enough to handle reasoning, summarization and question answering seriously, small enough to run locally on hardware with sufficient VRAM. The weights are yours to download, and the API price is modest.

Known for

Open weights: download and run it on your own hardware
Solid general reasoning and question answering for its size class
Competent summarization across varied text types
Shares architectural research with Google's Gemini family
Available via Hugging Face at google/gemma-2-27b-it

Watch out for

8,192-token context is short by current standards; long documents will need chunking.
Usage is governed by Google's Gemma Terms of Use, not a standard open-source licence.
At 27B parameters, local use demands meaningful VRAM — plan for 24 GB or more.

Best for

Prompts to try

Summarize a dense argument

Read the following passage and give me a three-paragraph summary: first, the core claim; second, the main evidence offered; third, the weakest point in the argument. Then tell me in one sentence whether the argument holds. Paste your text below this line.

Reason through a decision

I need to decide whether to migrate a small production app from a single PostgreSQL instance to a managed multi-region setup. The app has 50,000 monthly active users, read-heavy traffic, and a two-person engineering team. Walk me through the trade-offs and give me a clear recommendation with your reasoning.

Answer a layered question

Explain why central banks raise interest rates to fight inflation, then explain the main way this can backfire, and finally tell me what indicator an economist would watch to know if it is working. Keep each part to two or three sentences.

Compare with

Gemini 4 Argon
API-only model
1,048,576 token context · $2.00/M input, $10.00/M output
Gemini 2.5 Pro Preview 06-05
API-only model
1,048,576 token context · $1.25/M input, $10.00/M output
Nano Banana Pro (Gemini 3 Pro Image)
API-only model
131,072 token context · $2.00/M input, $12.00/M output
Gemini 3.1 Flash Lite Preview
API-only model
1,048,576 token context · $0.25/M input, $1.50/M output

More text models from google

Questions people ask

Can I run Gemma 2 27B locally?: Yes — the weights are open and hosted at google/gemma-2-27b-it on Hugging Face. At 27B parameters you will want around 24 GB of VRAM for comfortable local inference; tools like Ollama or LM Studio can handle it.
What does Gemma 2 27B cost via API?: Google prices it at $0.65 per million tokens for both input and output, which is on the affordable end for a model of this size. The context window is 8,192 tokens.
How does Gemma 2 27B differ from Gemini models?: Gemma 2 27B is built on the same research as Gemini but is an open-weights release you can download and self-host; Gemini models are closed and API-only. Gemma 2 27B is also considerably smaller than the top Gemini tiers.

Captain's verdict
A capable open-weights model at a fair price — worth considering if local deployment or budget matters and you don't need a long context window.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

AI Models for Image, Video & Text Generation

Gemma 2 27B is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.

More Text / LLM models llm google reasoning summarization research local

Browse by Model Family