Gemma 3 12B IT by Nvidia | AI model information

The fastest Kimi K3, GLM 5.2 and MiniMax M3The fastest Kimi K3, GLM 5.2 and MiniMax M3

Discuss

Model details

Gemma 3 12B IT

Nvidiagoogle/gemma-3-12b-itgemma

Open provider page Provider docs

Quick Info

Provider: Nvidia
Model key: google/gemma-3-12b-it
Release date: Mar 12, 2025

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 16,384 tokens
Context window: 131,072 tokens

Latest news about Gemma 3 12B IT

Videos about Gemma 3 12B IT

Recent tweets and retweets from Nvidia

Jul 21, 2026, 4:38 PMUTC

Your Blender scenes just got an upgrade. 🤖 NVIDIA Omniverse libraries are now part of NVIDIA Agent Toolkit, so AI agents can handle physics, sensor behavior, and scene checks right inside Blender, helping you take your 3D worlds from visually complete to simulation…

Jul 27, 2026, 9:02 AMUTC

AI security advances when the industry builds in the open, together. We're introducing the Open Secure AI Alliance with industry leaders to develop new techniques and tools to safeguard software and agents. By sharing models, tooling and research in the open, we can broaden…

Jul 28, 2026, 4:05 PMUTC

The Open Secure AI Alliance is growing, with more organizations contributing expertise to help safeguard software and agents. nvda.ws/4pD8Fc5

Jul 27, 2026, 11:29 PMUTC

Translation queues and custom integrations can slow global launches. Our Digital Marketing team built an AI-powered localization platform with NVIDIA Nemotron Speech to change that. See the results ↓ nvda.ws/4wYUS22

Jul 27, 2026, 1:15 PMUTC

Korea’s AI moment came to San Francisco last week 🇰🇷 President Lee Jae Myung joined @JensenHuang and some of the biggest names in technology, industry and research to accelerate Korea’s full-stack AI ambitions.