Can I run Gemma 4 31B IT Turbo locally?

No. The weights are not publicly released, so it is API-only — you cannot download or self-host it.

What does it cost and how long is the context?

Pricing is $0.09 per million input tokens and $0.34 per million output tokens, with a 262,144-token context window.

How does this differ from other Gemma 4 models?

Google has not published a detailed comparison between Gemma 4 variants, but the Turbo label typically signals a speed or efficiency optimisation within a model family.

Gemma 4 31B it turbo

4653°

#llm #google #vision #reasoning #long context #budget

Open DeepInfra

google | 262,144 token context | $0.09/M input, $0.34/M output. Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.

Guides for this model

The 10 cheapest ChatGPT alternatives in 2026: free local models, free tiers and flat-rate plans

Open weights vs open source vs API-only: what you are actually allowed to do

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

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Gemma 4 31B IT Turbo is a multimodal model from Google DeepMind that takes text and image input and returns text. It sits in the mid-size range of the Gemma 4 family and comes with a 262,144-token context window. At under ten cents per million input tokens it is priced for volume use, making it worth a look if you need vision plus long-context reasoning without a large API bill.

Known for

262,144-token context window — handles very long documents in one pass.
Accepts image input alongside text, covering multimodal tasks.
Low input price of $0.09/M tokens keeps costs manageable at scale.
Part of Google DeepMind's Gemma 4 family, built for broad task coverage.

Watch out for

Weights are not publicly available; you are tied to the API, no local deployment.
Output tokens cost nearly four times the input rate — watch generation length in production.

Best for

Prompts to try

Analyse a dense document

Here is a long contract. Identify every clause that limits liability, summarise what each one says in plain English, and flag any that are unusual or one-sided. Be specific about section numbers.

Describe and reason about an image

I am attaching a screenshot of a data dashboard. List every metric shown, note any that look anomalous compared to the others, and suggest two possible explanations for each anomaly.

Multi-step reasoning problem

A warehouse ships 240 orders a day across three shifts of equal length. The morning shift handles 40% of orders, the afternoon shift 35%, and the night shift the rest. If the night shift adds one worker and output rises by 15%, how many orders does the night shift now process, and what is the new daily total?

Compare with

Gemini 3.8 Flash
API-only model
1,048,576 token context · $0.83/M input, $4.12/M output
Gemini 3 Flash Preview
API-only model
1,048,576 token context · $0.50/M input, $3.00/M output
Gemini 2.5 Flash Lite
API-only model
1,048,576 token context · $0.10/M input, $0.40/M output
Gemini 3.1 Flash Lite
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 4 31B IT Turbo locally?: No. The weights are not publicly released, so it is API-only — you cannot download or self-host it.
What does it cost and how long is the context?: Pricing is $0.09 per million input tokens and $0.34 per million output tokens, with a 262,144-token context window.
How does this differ from other Gemma 4 models?: Google has not published a detailed comparison between Gemma 4 variants, but the Turbo label typically signals a speed or efficiency optimisation within a model family.

Captain's verdict
A genuinely cheap entry point for long-context vision tasks — just remember you are renting it, not owning it.

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.

How to install

How to Install Ollama and Run a Local AI (Windows, Mac, Linux)

Similar Models

AI Models for Image, Video & Text Generation

Gemma 4 31B it turbo 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 and check its heat score to see how it is trending.

More Text / LLM models llm google vision reasoning long context budget

Browse by Model Family