Multimodal Input
Processes both images and text as input in a single request, enabling tasks like visual question answering, image description, and document analysis.
Google
Gemma 3.2
Gemma 3 27B is an open-weight multimodal language model developed by Google DeepMind as the flagship model in the Gemma 3 family. It accepts both image and text inputs and generates text outputs, supporting over 140 languages and a context window of 128,000 tokens — sixteen times larger than the previous Gemma 2 generation. The model is built on the same research foundation as Google's Gemini models and was released in March 2025. Gemma 3 27B is designed to run in resource-constrained environments, including on a single consumer GPU with 24GB of VRAM, as well as on laptops, desktops, and cloud infrastructure. It is well-suited for tasks such as visual question answering, document analysis, multilingual text generation, summarization, coding assistance, and logical reasoning. Its combination of multimodal input support, large context handling, and open-weight availability makes it a practical choice for developers building applications that require flexible deployment options.
March 2025
128,000 context
8,000 tokens output
Multimodal Input
128K Context Window
Multilingual Generation
Reasoning & Analysis
Code Generation
Flexible Deployment
Model Overview
High-signal model metadata in a structured two-column overview table.
Provider
The entity that provides this model.
Google
Input Context Window
The number of tokens supported by the input context window.
128,000
tokens
Maximum Output Tokens
The number of tokens that can be generated by the model in a single request.
8,000 tokens
tokens
Open Source
Whether the model's code is available for public use.
No
Release Date
When the model was first released.
March 2025
Knowledge Cut-off Date
When the model's knowledge was last updated.
March 2025
API Providers
The providers that offer this model. This is not an exhaustive list.
Google
Modalities
Types of data this model can process.
Text
Image
What is Gemma 3.2
A fuller summary of positioning, capabilities, and source-specific details for Gemma 3.2.
Gemma 3 27B is an open-weight multimodal language model developed by Google DeepMind as the flagship model in the Gemma 3 family. It accepts both image and text inputs and generates text outputs, supporting over 140 languages and a context window of 128,000 tokens — sixteen times larger than the previous Gemma 2 generation. The model is built on the same research foundation as Google's Gemini models and was released in March 2025.
Gemma 3 27B is designed to run in resource-constrained environments, including on a single consumer GPU with 24GB of VRAM, as well as on laptops, desktops, and cloud infrastructure. It is well-suited for tasks such as visual question answering, document analysis, multilingual text generation, summarization, coding assistance, and logical reasoning. Its combination of multimodal input support, large context handling, and open-weight availability makes it a practical choice for developers building applications that require flexible deployment options.
Capabilities
What Gemma 3.2 supports
128K Context Window
Handles up to 128,000 tokens of input per request, allowing analysis of long documents, large codebases, and extended multi-turn conversations.
Multilingual Generation
Generates and understands text in 140+ languages, making it suitable for globally-facing applications and cross-language tasks.
Reasoning & Analysis
Performs multi-step logical reasoning, summarization, and question answering across complex inputs including code and structured documents.
Code Generation
Generates, explains, and debugs code across common programming languages as part of its general text generation capabilities.
Flexible Deployment
Runs locally on a single GPU with 24GB VRAM (e.g., RTX 3090) as well as on cloud infrastructure, with open weights available for download.
Pricing for Gemma 3.2
Primary API pricing shown in the same “quick compare” spirit as the reference page.
Input tokens
$0.10
Per million tokens
Output tokens
N/A
Per million tokens
Price Comparison
Additional usage-cost dimensions synced into the project for this model.
maxTemperature
1
maxResponseSize
8,000 tokens
API Access & Providers
Places where this model is available, based on the synced detail-page metadata.
Google
Model Performance
Benchmark scores synced from the current model source and normalized into the local catalog.
| Benchmark | Score |
|---|---|
|
AIME 2024
American math olympiad problems
|
|
|
GPQA Diamond
PhD-level science questions (biology, physics, chemistry)
|
|
|
HLE
Questions that challenge frontier models across many domains
|
|
|
LiveCodeBench
Real-world coding tasks from recent competitions
|
|
|
MATH-500
Undergraduate and competition-level math problems
|
|
|
MMLU-Pro
Expert knowledge across 14 academic disciplines
|
|
|
SciCode
Scientific research coding and numerical methods
|
Resources & Documentation
Official model cards, release notes, docs, and other references synced from the source page.
Model Card (Hugging Face)
Other
→
Announcement Blog Post
Announcements
→
Gemma 3 Technical Report
Research
→
Official Documentation
Documentation
→
NVIDIA NIM Model Card
Other
→
Gemma on Google AI for Developers
Documentation
→
Gemma GitHub Repository
Open Source
→
Try Gemma 3 on Google AI Studio
Playground
→
Related Daily Briefs
Recent daily stories tied to Gemma 3.2 through direct model mentions or provider-level coverage.
Hugging Face and Google are pushing more practical AI product shifts.
2026-07-21
AI Models
AI API
Google and Qwen move deeper into real workflows.
2026-07-21
AI API
Integration
Mistral and Google move deeper into real workflows.
2026-07-21
AI Models
Partnership
OpenAI and Google are raising the stakes for enterprise adoption.
2026-07-10
AI Models
FAQ
Common questions about Gemma 3.2
What is the context window size for Gemma 3 27B?
Gemma 3 27B supports a context window of 128,000 tokens, which is sixteen times larger than the previous Gemma 2 generation.
Does Gemma 3 27B support image inputs?
Yes. Gemma 3 27B is a multimodal model that accepts both image and text as inputs, enabling tasks such as visual question answering, image description, and document analysis.
What languages does Gemma 3 27B support?
The model supports over 140 languages for both input understanding and text generation.
What is the training data cutoff for Gemma 3 27B?
Based on the available metadata, the model's training date is listed as March 2025. For precise knowledge cutoff details, refer to the official Gemma 3 Technical Report.
Can Gemma 3 27B be run locally?
Yes. The model is open-weight and can be deployed locally on a single GPU with 24GB of VRAM, such as an NVIDIA RTX 3090, as well as on laptops, desktops, or cloud infrastructure.
Is Gemma 3 27B free to use?
Gemma 3 27B is an open-weight model, meaning the weights are publicly available. Usage costs on MindStudio depend on the underlying inference provider (DeepInfra in this case); consult MindStudio's pricing page for current rates.
More models from Google
Continue browsing adjacent models from the same provider.