
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 RTX PC users.
The era of the AI PC is here, and it's powered by NVIDIA RTX and GeForce RTX technologies. With it comes a new way to evaluate performance for AI-accelerated tasks, and a new language that can be daunting to decipher when choosing between the desktops and laptops available.
While PC gamers understand frames per second (FPS) and similar stats, measuring AI performance requires new metrics.
Coming Out on TOPS The first baseline is TOPS, or trillions of operations per second. Trillions is the important word here - the processing numbers behind generative AI tasks are absolutely massive. Think of TOPS as a raw performance metric, similar to an engine's horsepower rating. More is better.
Compare, for example, the recently announced Copilot+ PC lineup by Microsoft, which includes neural processing units (NPUs) able to perform upwards of 40 TOPS. Performing 40 TOPS is sufficient for some light AI-assisted tasks, like asking a local chatbot where yesterday's notes are.
But many generative AI tasks are more demanding. NVIDIA RTX and GeForce RTX GPUs deliver unprecedented performance across all generative tasks - the GeForce RTX 4090 GPU offers more than 1,300 TOPS. This is the kind of horsepower needed to handle AI-assisted digital content creation, AI super resolution in PC gaming, generating images from text or video, querying local large language models (LLMs) and more.
Insert Tokens to Play TOPS is only the beginning of the story. LLM performance is measured in the number of tokens generated by the model.
Tokens are the output of the LLM. A token can be a word in a sentence, or even a smaller fragment like punctuation or whitespace. Performance for AI-accelerated tasks can be measured in tokens per second.
Another important factor is batch size, or the number of inputs processed simultaneously in a single inference pass. As an LLM will sit at the core of many modern AI systems, the ability to handle multiple inputs (e.g. from a single application or across multiple applications) will be a key differentiator. While larger batch sizes improve performance for concurrent inputs, they also require more memory, especially when combined with larger models.
The more you batch, the more (time) you save. RTX GPUs are exceptionally well-suited for LLMs due to their large amounts of dedicated video random access memory (VRAM), Tensor Cores and TensorRT-LLM software.
GeForce RTX GPUs offer up to 24GB of high-speed VRAM, and NVIDIA RTX GPUs up to 48GB, which can handle larger models and enable higher batch sizes. RTX GPUs also take advantage of Tensor Cores - dedicated AI accelerators that dramatically speed up the computationally intensive operations required for deep learning and generative AI models. That maximum performance is easily accessed when an application uses the NVIDIA TensorRT software development kit (SDK), which unlocks the highest-performance generative AI on the more than 100 million Windows PCs and workstations powered by RTX GPUs.
The combination of memory, dedicated AI accelerators and optimized software gives RTX GPUs massive throughput gains, especially as batch sizes increase.
Text-to-Image, Faster Than Ever Measuring image generation speed is another way to evaluate performance. One of the most straightforward ways uses Stable Diffusion, a popular image-based AI model that allows users to easily convert text descriptions into complex visual representations.
With Stable Diffusion, users can quickly create and refine images from text prompts to achieve their desired output. When using an RTX GPU, these results can be generated faster than processing the AI model on a CPU or NPU.
That performance is even higher when using the TensorRT extension for the popular Automatic1111 interface. RTX users can generate images from prompts up to 2x faster with the SDXL Base checkpoint - significantly streamlining Stable Diffusion workflows.
ComfyUI, another popular Stable Diffusion user interface, added TensorRT acceleration last week. RTX users can now generate images from prompts up to 60% faster, and can even convert these images to videos using Stable Video Diffuson up to 70% faster with TensorRT.
TensorRT acceleration can be put to the test in the new UL Procyon AI Image Generation benchmark, which delivers speedups of 50% on a GeForce RTX 4080 SUPER GPU compared with the fastest non-TensorRT implementation.
TensorRT acceleration will soon be released for Stable Diffusion 3 - Stability AI's new, highly anticipated text-to-image model - boosting performance by 50%. Plus, the new TensorRT-Model Optimizer enables accelerating performance even further. This results in a 70% speedup compared with the non-TensorRT implementation, along with a 50% reduction in memory consumption.
Of course, seeing is believing - the true test is in the real-world use case of iterating on an original prompt. Users can refine image generation by tweaking prompts significantly faster on RTX GPUs, taking seconds per iteration compared with minutes on a Macbook Pro M3 Max. Plus, users get both speed and security with everything remaining private when running locally on an RTX-powered PC or workstation.
The Results Are in and Open Sourced But don't just take our word for it. The team of AI researchers and engineers behind the open-source Jan.ai recently integrated TensorRT-LLM into its local chatbot app, then tested these optimizations for themselves.
Source: Jan.ai The researchers tested its implementation of TensorRT-LLM against the open-source llama.cpp inference engine across a variety of GPUs and CPUs used by the community. They found that TensorRT is 30-70% faster than llam
North America Stories
25/03/2026
Live match directors Sarah Cheadle (Sky Sports), Rob Levi (TNT Sports), and Andrew Swift (BBC Sport) sit down with the Premier League's Rachel Nightingale t...
25/03/2026
The senior from Upstate New York is manning the mic while also interning for the athletic department's sports-information team
In the live-sports-video ind...
25/03/2026
Synamedia has announced ContentArmor Edge Watermarking, a server-side solution t...
25/03/2026
SES has announced meoSphere, a medium Earth orbit (MEO) satellite network targeted for operation by 2030. The first phase will pair SES-developed software-defin...
25/03/2026
TVU Networks is working with Reuters on a phased migration from satellite to a c...
25/03/2026
Nielsen has announced three senior appointments. Seth Ladetsky has been named Head of Global Sports. Trevor Fellows will lead Nielsen's advertiser and agenc...
25/03/2026
Anoki and Amagi have launched In-Scene Ads powered by Anoki ContextIQ across Amagi's portfolio of in-content ad formats for Free Ad-supported Streaming TV (...
25/03/2026
Arkona Technologies will announce a series of enhancements to its BLADE//runner platform at NAB 2026 (Booth C.1808). The updates focus on usability and workflow...
25/03/2026
Daktronics has installed two tower displays and a video wall in the Lexus Club at Petco Park in San Diego ahead of the 2026 season.
Continuing to improve the ...
25/03/2026
MultiDyne Video & Fiber Optic Systems is celebrating its 50th anniversary as NAB Show 2026 approaches. The company was founded in 1976 by Vincent Jachetta, an N...
25/03/2026
IPC, a provider of integrated communication solutions, will make its NAB 2026 de...
25/03/2026
Live production categories were led by NBC, FOX, and ESPN's NFL coverage...
25/03/2026
The Atlanta Braves and Spectrum have announced a multiyear distribution agreemen...
25/03/2026
(L-R) Charlie Tyrell and Daniel Roher attend The AI Doc: Or How I Became An Apocaloptimist Premiere during the 2026 Sundance Film Festival at The Ray Theatre ...
25/03/2026
L3Harris Technologies and RFTEQ Pty Ltd signed a memorandum of understanding to ...
25/03/2026
L3Harris delivers combat-ready Torpedo Tube Launch and Recovery system, which deploys and retrieves Iver4 900 autonomous underwater vehicles through submarine t...
25/03/2026
The company expands leadership team under Chief Revenue Officer Amilcar Perez
S...
25/03/2026
Winter Olympic Games Opening Ceremony features in top 10 programmes of the month...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
Providing wide view timing visibility across the entire production chain...
25/03/2026
Continuing development drives advances in security, availability, access and connectivity...
25/03/2026
Caudalie, the renowned French cosmetics brand, has unveiled a state-of-the-art 200-seat auditorium at its new headquarters in the historic Marais district of ce...
25/03/2026
Telestream, a global leader in media workflow technologies, today announced expanded integration with Adobe Premiere, Adobe Media Encoder (AME), and Frame.io, d...
25/03/2026
Marshall Electronics is expanding its lineup of high-performance POV cameras designed for broadcast, live production and professional AV applications with the d...
25/03/2026
OOONA, a global provider of professional management and production tools for the media localization industry, announced today that it has been awarded the TPN G...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
SipRadius, specialists in secure, low-latency media transport, will drive innovation and interoperability still further with the launch of the SipMX Alliance at...
25/03/2026
QuickLink, a leading provider of award-winning video production and remote contribution solutions, will showcase its award-winning StudioPro ecosystem at The 2...
25/03/2026
Alfalite, the only European manufacturer of LED screens, will once again be present at NAB Show, the leading global event for the broadcast, media and entertain...
25/03/2026
PC, a leading provider of integrated communication solutions, will make its NAB 2026 Show debut in Booth C 3341. The company will highlight the newly branded On...
25/03/2026
Open video transport network simplifies satellite transition with new partnerships and global reach as spectrum auction nears
LTN will demonstrate how its purp...
25/03/2026
Test & measurement innovator, Leader Electronics, will present the full range of Leader, PHABRIX and LeaderPhabrix T&M solutions at the NAB Show, which takes pl...
25/03/2026
MNC Software, a global leader in network management and operational support systems tailored to the broadcast and media industry, today announced the appointmen...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
25/03/2026
Starfish highlights flexible TS Splicer releases and new Monitoring Dashboard at...
25/03/2026
XLNTSOUND Elevates Video Production with Blackmagic Design
Brie Clayton March 24, 2026
0 Comments
Audio company upgrades workflow with Blackmagic Cine...
25/03/2026
First Time Exhibitor IPC Introduces One Link Keypanels for One Connect Intercom ...
25/03/2026
Back to All News
Netflix Announces the Start of Production for Reasonable Doubts
Entertainment
25 March 2026
GlobalSpain
Link copied to clipboard
Download...
25/03/2026
Back to All News
2026 World Baseball Classic Becomes the Most-Watched Program ...
25/03/2026
NBC Sports Deploys viztrick AiDi to Stream Live Events in 9:16 Mobile-First Form...
25/03/2026
At the half-time whistle of the UEFA EURO 2020 round of 16 football match betwee...
24/03/2026
Utah Scientific to Showcase a Variety of Hybrid SDI/IP Innovations at the 2026 N...
24/03/2026
Mediaproxy will showcase an updated version of its LogPlayer interface at NAB Sh...
24/03/2026
C gep de Jonqui re, a public college in Qu bec, has upgraded its TV studio complex with five Calrec Brio consoles and a Dante IP network. The installation was c...
24/03/2026
The American Association of Professional Baseball (AAPB) has announced new and r...
24/03/2026
National Telecom Public Company Limited (NT) used Ateme's KYRION platform fo...
24/03/2026
Grass Valley has expanded its relationship with ImSoPROD, the TV production entity of FDJ United, with the deployment of LDX C98 compact cameras across its nati...