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
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
13/11/2026
The UIM E1 Series wraps its third season this week with the Bombay Sapphire E1 Miami GP, Nov. 11-14, on Biscayne Bay at the Miami Seaplane Base on Watson Island...
13/11/2026
In-venue and creative video staffers at the professional and collegiate level ha...
13/11/2026
Singer-songwriter Benson Boone will headline entertainment for the Discover NHL Winter Classic between the Utah Mammoth and Colorado Avalanche at Rice-Eccles St...
13/11/2026
Blackmagic Design has announced the Blackmagic Ambisonic Microphone, a 7th order ambisonic microphone array that captures spatial audio for immersive video prod...
13/11/2026
SMPTE has announced that The Studio B&H and Riedel Communications will provide the video infrastructure and communications technology for the Solutions Hub at t...
13/11/2026
The Hollywood Professional Association (HPA) has announced the theme and program focus for the 2027 HPA Tech Retreat, which takes place Feb. 14-18, 2027, in La ...
13/11/2026
Football Manager 27 Touch is available on Apple Arcade starting today. The game ...
13/11/2026
MotoGP has announced a two-year media rights agreement with ESPN covering the Un...
13/11/2026
Apple Sports, the free iPhone app, has added the Ultimate Fighting Championship (UFC) to its lineup of supported sports, in time for Saturday's UFC 334. The...
13/11/2026
The NBA and Fanatics Studios, the joint venture between Fanatics and entertainme...
13/11/2026
ESPN held its annual EDGE Innovation Conference last night and offered up an ove...
13/11/2026
Regional sports network gives Ithaca College, SUNY Cortland students a platform to thrive
One of the biggest games in Division III college football will be pla...
13/11/2026
Studer-inspired 500-series PWM compressor unveiled
The HLabs range already includes a couple of Studer-inspired offerings in the form of the PRE169 and EQ16...
13/11/2026
Download Now!
To view the white paper, please enter the following details:
--
First Name* First Name
Company*
Country* Please select your countryA...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Blue Lucy, the workflow orchestration and integration platform for broadcasters, rights owners and localisation companies, today announced an integration with c...
13/11/2026
Krotos announces Black Friday offers on Studio Pro and Studio Max
Brie Clayton November 12, 2026
0 Comments
First-year annual plans start at US$195.99...
13/11/2026
Blackmagic Design Announces Blackmagic Ambisonic Microphone
Brie Clayton November 12, 2026
0 Comments
New 7th order ambisonic microphone with 108 MEMS...
13/11/2026
Meet the Berklee Student Setting Planetary Motion to Music With his compositional platform SoniKosmos, Javier Roqueni aims to make the universe the ultimate i...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , er...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , er...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Share
{alert(Link copied)}).catch(err => {console.error(Failed to copy: , err)}) data-platform=copy_link data-action= class=font-ui-heading py-2 text-sm tex...
13/11/2026
Amagi, the media industry cloud company, today announced a partnership with Golden Times Media Technology (stock code 920021.BJ), a Beijing-based media and tech...
13/11/2026
CGI (TSX: GIB.A) (NYSE: GIB), one of the largest independent IT and business consulting services firms in the world, together with its Malaysian partner, Cedar ...
13/11/2026
SMPTE, the home for media professionals, technologists and engineers, today announced that The Studio B&H and Riedel Communications will provide the video infra...
13/11/2026
iWedia, a global leader in connected TV software solutions, will present its software-first approach to DRAM optimization at Android TV APAC Summit 2026 in Bang...
13/11/2026
Beginning today, November 13, Apple HomeView is available for purchase at Apple Store locations, on the Apple Store online, and in the Apple Store app in select...
13/11/2026
From pediatric research to smart hospitals, AI is helping care teams spend less time on routine tasks and more time with patients.
Health systems and startups...
12/11/2026
Industry leaders examine how Dynamic Media Facility, Media eXchange Layer, and c...
12/11/2026
The junior Tar Heel is embracing the technical and creative challenges of live production while emerging as a leader and mentor in the control room...
12/11/2026
Gracenote, Nielsen's content intelligence business, has released its fifth a...
12/11/2026
RTL Deutschland will bring the NHL to free-to-air TV in Germany starting Nov. 30...
12/11/2026
Clear-Com supported On Air 2026, a 24-hour student-led broadcast connecting 45 u...
12/11/2026
uniqFEED has opened a Remote Operations Center (ROC) in Madrid, Spain. It is already operational, delivering virtual advertising for LaLiga matches. The ROC is ...
12/11/2026
Disney, ESPN and the NBA will present Dunk the Halls, the third real-time animated NBA game using Sony's Beyond Sports data visualization technology, on Chr...
12/11/2026
Van Wagner has launched Van Wagner RELAY, a digital platform for official athlet...
12/11/2026
Deal brings together two of the industry's most established graphics brands and significantly expands Vizrt's footprint in U.S. sports and regional broa...
12/11/2026
Euro TV Production GmbH of Austria has upgraded its outside broadcast vehicle with Lawo technology. The mc 36 Classic console in service since 2019 was replaced...
12/11/2026
Tagboard has launched Spark Resize, an AI-assisted tool now in beta that takes an existing graphic and produces a new version for a different aspect ratio or sc...
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.
