Vision, Video and Audio Capabilities: E nables rich multimodal interactions for object recognition, automated speech recognition, and document or video intelligence.
Interleaved Multimodal Input: M ix text and images in any order within a single prompt.
Multilingual: Out-of-the-box support for 35+ languages, pretrained on 140+ languages.
The E2B and E4B models are built for ultraefficient, low-latency inference at the edge, running completely offline with near-zero latency across many devices including Jetson Nano modules.
The 26B and 31B models are designed for high-performance reasoning and developer-centric workflows, making them well suited for agentic AI. Optimized to deliver state-of-the-art, accessible reasoning, these models run efficiently on NVIDIA RTX GPUs and DGX Spark — powering development environments, coding assistants and agent-driven workflows.
As local agentic AI continues to gain momentum, applications like OpenClaw are enabling always-on AI assistants on RTX PCs, workstations and DGX Spark. The latest Gemma 4 models are compatible with OpenClaw, allowing users to build capable local agents that draw context from personal files, applications and workflows to automate tasks. Learn how to run OpenClaw for free on RTX GPUs and DGX Spark or using the DGX Spark OpenClaw playbook .
Check out the Google DeepMind announcement blog to l earn more about the latest additions to Gemma 4 family.
NVIDIA has collaborated with Ollama and llama.cpp to provide the best local deployment experience for each of the Gemma 4 models.
To use Gemma 4 locally, users can download Ollama to run Gemma 4 models or install llama.cpp and pair it with the Gemma 4 GGUF Hugging Face checkpoint. Additionally, Unsloth provides day-one support with optimized and quantized models for efficient local fine-tuning and deployment via Unsloth Studio. Start running and fine-tuning Gemma 4 in Unsloth Studio today.
Running open models like the Gemma 4 family on NVIDIA GPUs achieves optimal performance because NVIDIA Tensor Cores accelerate AI inference workloads to deliver higher throughput and lower latency for local execution. Plus, the CUDA software stack ensures broad compatibility across leading frameworks and tools, enabling new models to run efficiently from day one.
This combination allows open models like Gemma 4 to scale across a wide range of systems — from Jetson Orin Nano at the edge to RTX PCs, workstations and DGX Spark — without requiring extensive optimization.
Check out the NVIDIA technical blog for more details on how to get started with Gemma 4 on NVIDIA GPUs and learn more about NVIDIA’s work on open models .
✨ Catch up on RTX AI Garage blogs for a host of agentic AI announcements from NVIDIA GTC, such as new open models for local agents. These models include NVIDIA Nemotron 3 Nano 4B and Nemotron 3 Super 120B, and optimizations for Qwen 3.5 and Mistral Small 4.
NVIDIA recently introduced NVIDIA NemoClaw, an open source stack that optimizes OpenClaw experiences on NVIDIA devices by increasing security and supporting local models.
🚀 Accomplish.ai announced Accomplish FREE, a no-cost version of its open source desktop AI agent with built-in models. It harnesses NVIDIA GPUs to run open weight models locally, while a hybrid router dynamically balances workloads between local RTX hardware and the cloud — enabling fast, private, zero-configuration execution without requiring an application programming interface key.
Follow NVIDIA Workstation on LinkedIn and X .
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://blogs.nvidia.com/blog/rtx-ai-garage-open-models-google-gemma-4/#primary
- https://blogs.nvidia.com/blog/author/mfukuyama/
- https://blogs.nvidia.com/blog/rtx-ai-garage-open-models-google-gemma-4/#disqus_thread
- One of JavaScript's most popular libraries compromised by hackers — Axios npm package hit in supply chain attack that deployed a cross-platform RAT
- NES-inspired synthesizer doubles as a working game console — luggable polyphonic synth plays chip tunes and NES cartridges, too
- Act fast to grab this 32GB Corsair Vengeance DDR5 RAM for just $269, the cheapest kit in months — limited-time Woot deal is now $100 cheaper than the next-best
- The global helium shortage is a direct threat to the chipmaking supply chain — disruption impacts critical processes, high-capacity HDDs, and alternative suppli
- Into the Omniverse: NVIDIA GTC Showcases Virtual Worlds Powering the Physical AI Era
Informational only. No financial advice. Do your own research.