Gemma 4 31B
8875°
Run this model
Offers / Ads
Google | 262,144 token context | $0.20/M input, $0.40/M output. Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.
Guides for this model
How to Install Ollama and Run a Local AI (Windows, Mac, Linux)
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 to choose an AI model in October 2026: the closed source news, then the open weights worth downloading
How much VRAM do I actually need for local AI?
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Gemma 4 31B is Google DeepMind's 30.7B dense multimodal model, taking text and image input and producing text output with a 256K token context window. Open weights under Apache 2.0 make it one of the more permissive large models you can actually run yourself. It suits developers and researchers who want strong coding, reasoning, and document understanding without a closed-API dependency.
Known for
- 256K token context window, useful for long documents and codebases.
- Configurable thinking mode lets you dial reasoning depth up or down.
- Native function calling built in, not bolted on.
- Multilingual across 140+ languages.
- Apache 2.0 licence: commercial use, fine-tuning, redistribution all allowed.
Watch out for
- Image and text input only at this size; audio is reserved for the smaller E2B, E4B, and 12B variants.
- 30.7B dense weights demand serious VRAM to run locally — a 24 GB card is the realistic floor.
- API pricing is low but not free; self-hosting shifts cost to hardware.
Prompts to try
Debug a tricky async bug
Here is a Python async function that occasionally raises a RuntimeError about an event loop being closed. Walk through what is likely causing it, then rewrite the function so it handles the event loop lifecycle correctly. Explain each change you make and why it fixes the problem.
Reason through a logic puzzle
Five engineers join a project on consecutive days, Monday through Friday. Alex joins before Dana. Casey joins after Blake but before Elliot. Dana joins on Wednesday. Blake does not join on Monday. In what order did they join, and how did you work it out step by step?
Extract structure from a document
I am attaching a dense technical specification PDF. Pull out every requirement statement, label each one with a unique ID, classify it as functional or non-functional, and return the results as a JSON array with fields: id, text, type, and section.
Compare with
- Gemini 3.8 FlashAPI-only model1,048,576 token context · $0.83/M input, $4.12/M output
- Gemini 3 Flash PreviewAPI-only model1,048,576 token context · $0.50/M input, $3.00/M output
- Gemini 2.5 Flash LiteAPI-only model1,048,576 token context · $0.10/M input, $0.40/M output
- Gemini 3.1 Flash LiteAPI-only model1,048,576 token context · $0.25/M input, $1.50/M output
More text models from google
Questions people ask
- Can I run Gemma 4 31B locally?
- Yes — the weights are open under Apache 2.0 and available on Hugging Face at google/gemma-4-31B-it, so you can download and run them yourself, though the 30.7B dense parameter count means you will need substantial VRAM.
- What does it cost and how long is the context?
- Via API it is priced at $0.09 per million input tokens and $0.34 per million output tokens, with a 256K token context window.
- How does the 31B differ from the other Gemma 4 sizes?
- The 31B is the largest dense model in the Gemma 4 family and shares the 256K context window with the 12B, but unlike the smaller variants it does not support audio input — only text and images.
Captain's verdictA genuinely open, commercially usable 30B model with a long context and real reasoning depth — rare enough to be worth your attention.
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.
Also ranked: #41 Hottest Text / LLM model · #41 Hottest Text / LLM text model
Not this creator?
Get your own badge
Gemma 4 31B Popularity Trend
Heat score since 2 Apr 2026
Heat score
8,875°
This week
▲
33.0%
8,837° then, 8,875° now
This month
▲
267%
8,702° then, 8,875° now
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+1,583°
OpenRouter tokens
1,892,201,174,485 tokens this model processed through OpenRouter in the last 30 days, prompts and answers together. Every 10,000,000 tokens count as one download in the download term, 189,220 in all; the last day's tokens join the adoption rate. Source: OpenRouter (openrouter.ai/rankings).
+292°
Adoption rate
About 7,725 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 8,875°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.189,220 download-equivalents in all, from OpenRouter tokens. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+1,583°8,583°running total
- 3Add the adoption rate.About 7,725 downloads a day right now, measured between two readings, at a quarter of the weight.+292°8,875°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,875°
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 this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Gemma 4 31B 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.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153