
Editor's note: This post is part of the AI Decoded series, which demystifies AI by making the technology more accessible, and showcases new hardware, software, tools and accelerations for GeForce RTX PC and NVIDIA RTX workstation users.
From games and content creation apps to software development and productivity tools, AI is increasingly being integrated into applications to enhance user experiences and boost efficiency.
Those efficiency boosts extend to everyday tasks, like web browsing. Brave, a privacy-focused web browser, recently launched a smart AI assistant called Leo AI that, in addition to providing search results, helps users summarize articles and videos, surface insights from documents, answer questions and more.
Leo AI helps users summarize articles and videos, surface insights from documents, answer questions and more. The technology behind Brave and other AI-powered tools is a combination of hardware, libraries and ecosystem software that's optimized for the unique needs of AI.
Why Software Matters NVIDIA GPUs power the world's AI, whether running in the data center or on a local PC. They contain Tensor Cores, which are specifically designed to accelerate AI applications like Leo AI through massively parallel number crunching - rapidly processing the huge number of calculations needed for AI simultaneously, rather than doing them one at a time.
But great hardware only matters if applications can make efficient use of it. The software running on top of GPUs is just as critical for delivering the fastest, most responsive AI experience.
The first layer is the AI inference library, which acts like a translator that takes requests for common AI tasks and converts them to specific instructions for the hardware to run. Popular inference libraries include NVIDIA TensorRT, Microsoft's DirectML and the one used by Brave and Leo AI via Ollama, called llama.cpp.
Llama.cpp is an open-source library and framework. Through CUDA - the NVIDIA software application programming interface that enables developers to optimize for GeForce RTX and NVIDIA RTX GPUs - provides Tensor Core acceleration for hundreds of models, including popular large language models (LLMs) like Gemma, Llama 3, Mistral and Phi.
On top of the inference library, applications often use a local inference server to simplify integration. The inference server handles tasks like downloading and configuring specific AI models so that the application doesn't have to.
Ollama is an open-source project that sits on top of llama.cpp and provides access to the library's features. It supports an ecosystem of applications that deliver local AI capabilities. Across the entire technology stack, NVIDIA works to optimize tools like Ollama for NVIDIA hardware to deliver faster, more responsive AI experiences on RTX.
Applications like Brave's Leo AI can access RTX-powered AI acceleration to enhance user experiences. NVIDIA's focus on optimization spans the entire technology stack - from hardware to system software to the inference libraries and tools that enable applications to deliver faster, more responsive AI experiences on RTX.
Local vs. Cloud Brave's Leo AI can run in the cloud or locally on a PC through Ollama.
There are many benefits to processing inference using a local model. By not sending prompts to an outside server for processing, the experience is private and always available. For instance, Brave users can get help with their finances or medical questions without sending anything to the cloud. Running locally also eliminates the need to pay for unrestricted cloud access. With Ollama, users can take advantage of a wider variety of open-source models than most hosted services, which often support only one or two varieties of the same AI model.
Users can also interact with models that have different specializations, such as bilingual models, compact-sized models, code generation models and more.
RTX enables a fast, responsive experience when running AI locally. Using the Llama 3 8B model with llama.cpp, users can expect responses up to 149 tokens per second - or approximately 110 words per second. When using Brave with Leo AI and Ollama, this means snappier responses to questions, requests for content summaries and more.
NVIDIA internal throughput performance measurements on NVIDIA GeForce RTX GPUs, featuring a Llama 3 8B model with an input sequence length of 100 tokens, generating 100 tokens. Get Started With Brave With Leo AI and Ollama Installing Ollama is easy - download the installer from the project's website and let it run in the background. From a command prompt, users can download and install a wide variety of supported models, then interact with the local model from the command line.
For simple instructions on how to add local LLM support via Ollama, read the company's blog. Once configured to point to Ollama, Leo AI will use the locally hosted LLM for prompts and queries. Users can also switch between cloud and local models at any time.
Brave with Leo AI running on Ollama and accelerated by RTX is a great way to get more out of your browsing experience. You can even summarize and ask questions about AI Decoded blogs! Developers can learn more about how to use Ollama and llama.cpp in the NVIDIA Technical Blog.
Generative AI is transforming gaming, videoconferencing and interactive experiences of all kinds. Make sense of what's new and what's next by subscribing to the AI Decoded newsletter.
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
09/10/2026
September 10 2026, 06:00 (PDT) Dolby Expands Dolby OptiView Platform with New Capabilities at IBC 2026
New Sports Intelligence helps providers better unders...
07/10/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...
24/09/2026
Manifold Technologies Appoints Ryhaan Williams as CCO for North America
Brie Clayton September 24, 2026
0 Comments
Brings three decades of broadcast e...
24/09/2026
UNIFACHA Expands Educational Program with DaVinci Resolve Studio
Brie Clayton September 24, 2026
0 Comments
Brazilian university empowers next generat...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Viewers watching videos from the Austrian Parliament online will soon find it easier to verify the authenticity of the content. Big Blue Marble, an internationa...
24/09/2026
nsign, the digital signage SaaS platform built around its Simplify Complexity principle, is now officially certified for BRAVIA Professional Displays from Son...
24/09/2026
Encompass Digital Media today announced the successful migration of multiple Viaplay free-to-air channels, including TV3, TV6, TV8 and TV10, to its Altitude Sch...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/09/2026
Music Supervisor, Composer, and Mixing Engineer Santiago Uribe has built a career around producing music for film and television, contributing to more than 40 p...
24/09/2026
The North American Broadcasters Association (NABA) will hold a full-day cybersecurity summit focused on defending against growing cyber threats facing the broad...
24/09/2026
The home interiors retailer signs up for third year as sponsor
RT Commercial today announced that Harry Corry has signed up to a third year as sponsor of Live...
24/09/2026
When COVID-19 emerged, scientists had a crucial advantage: Decades of prior research on coronaviruses meant they understood the virus' key proteins well eno...
24/09/2026
RT Radio 1 Folk Awards Tickets on Sale
Dolores Keane to be inducted into the...
24/09/2026
A warped Manhattan is waiting in the cloud this week. Remedy Entertainment's CONTROL Resonant brings Dylan Faden's extraordinary abilities and a paranat...
23/09/2026
Four control rooms support B1G+ streams, videoboard shows, creative content, and...
23/09/2026
By Andrew Cohen, SVG Coorespondant
The Mountain West debuted its new Replay Operations Center at the start of this football season, bringing real-time collabor...
23/09/2026
The Taylorville, IL, native is pushing creative boundaries at Ball State, gaining reps across directing, technical directing, tape, and more than 100 ESPN+ broa...
23/09/2026
Alexander Heller, Nevada Jose, Will Brill, and Giselle Bonilla pose with cast members at The Musical premiere during the 2026 Sundance Film Festival at Eccles...
23/09/2026
Includes natural and processed patches
The Crow Hill Company's latest sample library captures a children's choir comprising a troupe of boys perform...
23/09/2026
Plug-in offers six bands of saturation
Kreuzberg Audio's product range includes a selection of plug-ins and virtual instruments aimed primarily at hard-...
23/09/2026
Latest DAW update now live
SoundBridge have announced that the latest update for the remote-collaboration-focused DAW is now available. The release of Sound...
23/09/2026
Koori Knockout returns home exclusively to NITV and SBS On Demand in 2026
11 September, 2026
Media releases
Fans can catch all the live action exclusively ...
23/09/2026
Rohde & Schwarz acquires NEOSAT and PHYTRONIC and strengthens its competencies i...
23/09/2026
1. ABOUT THE PROGRAMME
The National Film and Video Foundation (NFVF) invites applications from experienced producers who own or manage a South African product...
23/09/2026
The National Film and Video Foundation (NFVF) is pleased to announce the opening...
23/09/2026
Download Now!
To receive a short case study showcasing NHK Technologies, Inc. (NT) s audio setup, please enter the following details:
--
First Name* Fir...
23/09/2026
Nielsen CMI data reveals a changing fast-food landscape, with value, convenience...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
COW Jobs: Blender on Windows - Generalist - Remote
Brie Clayton September 23, 2026
0 Comments
Application Users - Blender on Windows - Generalist
Se...
23/09/2026
Version 1.8 recognised for new workflow tools, boosted control panel flexibility and ease of integration into IP networks...
23/09/2026
Hiltron Communications reports a successful 2026 International Broadcasting Convention, held at the RAI Amsterdam. Exhibiting on stand A37 in Hall 1, Hiltron ex...
23/09/2026
Reinforcing its long-term commitment to the Middle East and North Africa (MENA) broadcast market, LiveU is presenting the Q Era at CABSAT 2026, on Stand H1-D35 ...
23/09/2026
Agence France-Presse (AFP), a global news agency, and Dalet, a leading technology and service provider for media-rich organizations, today announced a partnersh...
23/09/2026
Berklee Connect Unlocks the Power of a Global Network Katie Vitolins BM '04 knows firsthand what Berklee's alumni community can make possible. Now she...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
23/09/2026
Westminster Schools, a K through 12 school in Atlanta, Georgia with approximately 2,000 students, has transformed its student broadcast and digital storytelling...
23/09/2026
The 2026 edition of CABSAT and SATExpo may have a new home and dates in the diary, but it still retains a strong presence from UK companies in the GREAT Britain...
23/09/2026
Glensound will return to CABSAT with new developments in professional monitoring and Dante interfacing, alongside its established commentary, esports and parlia...
23/09/2026
September 23 2026, 17:00 (PDT) Dolby and Meta Expand Dolby Atmos and Dolby Vision Across Metas Ecosystem
Across Meta AI glasses, Instagram, and VR devices, ...