
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
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 ...
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...
24/03/2026
The E.W. Scripps Company is launching Scripps Sports Network (SSN), a free, ad-s...
24/03/2026
NEP Group has launched NEP Platform, a new software orchestration system that un...
24/03/2026
Daktronics has partnered with the Arizona Diamondbacks to design, manufacture and install a new LED video display and three ribbon boards at Chase Field in Phoe...
24/03/2026
Grass Valley has completed an upgrade of University of Pittsburgh Athletics'...
24/03/2026
Daktronics is upgrading eight LED displays at Wrigley Field in Chicago, totaling more than 8,300 square feet, using the Daktronics Renew product line. The upgra...
24/03/2026
Advanced Systems Group has appointed Kevin Poole as Senior Project and Support Manager within the ASG Workflow and Tools practice. The position is newly created...
24/03/2026
In an increasingly streaming-centric world, protecting high-value live sports co...
24/03/2026
Mediaproxy will showcase an updated version of its LogPlayer interface at NAB Show, April 19-22 in Las Vegas, booth W1423. The update includes AI tools, native ...
24/03/2026
The production studio has worked with content juggernauts such as MrBeast, The R...
24/03/2026
The event will also feature a State of the Industry address from sports-media veteran and strategic advisor Patrick Crakes....
24/03/2026
Victory , a free sports streaming service owned by A Parent Media Co. (APMC), has launched its NWSL Sunday Night Soccer franchise. The platform says the launch ...
24/03/2026
Sports content in free streaming is still relatively scant, but it's growing, right along with its monetization capabilities
Streaming-tech company Wurl re...
24/03/2026
Directed by Greg DeHart, the doc will feature Sports Broadcasting Hall of Famers...
24/03/2026
For the first time ever, Tubi - Fox's free streaming service - is working w...
24/03/2026
L3Harris ramps up production of its VAMPIRE C-UxS system....
24/03/2026
For more than 70 years, L3Harris has delivered essential fuzes and safe-and-arm solutions that bring the might to multi-domain battlefields across the globe, ...
24/03/2026
Grass Valley has strengthened its long-standing relationship with ImSoPROD, the TV production entity of the FDJ United, with the deployment of Grass Valley LDX ...
24/03/2026
At the 2026 NAB Show in Las Vegas, Utah Scientific will spotlight its expanding portfolio of hybrid SDI/IP routing, conversion, control, and signal management s...
24/03/2026
Fresh off its global reveal at ISE 2026 in Barcelona, the new V410 live 4K encoder/decoder from Miri Technologies Inc. will make its North American debut at the...
24/03/2026
Cinegy GmbH, premier provider of software-defined television technology, will show how its solutions answer the real challenges facing content creators and broa...
24/03/2026
Canberra-based radio and online broadcast network ArtSound FM (https://artsound.fm/) has invested in DHD audio mixing consoles for two new studios at its headqu...
24/03/2026
IBC today announced the nine projects selected for its 2026 Accelerator Media Innovation Programme, bringing together organisations from across broadcast, strea...
24/03/2026
Mediaproxy, the global standard for software-based IP compliance monitoring and multiviewing solutions, will showcase the next generation of its industry-leadin...
24/03/2026
Underscoring its global reputation as one of Canada's most renowned colleges for television production, the C gep de Jonqui re public college in Qu bec has ...
24/03/2026
Leading video software provider Synamedia today announced the launch of the industry's first edge watermarking solution that enables faster disruption of pi...
24/03/2026
Experience Commerce, a leading full-service digital marketing agency and part of the Cheil SWA Group, has secured the annual social media mandate for Fiat Payme...
24/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/03/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
24/03/2026
Intinor introduces enhanced SRT monitoring, HDR transport and NDI Advanced suppo...
24/03/2026
Miri V410 Live 4K Encoder/Decoder to Make North American Debut at 2026 NAB Show
Brie Clayton March 23, 2026
0 Comments
Powerful new solution for strea...
24/03/2026
March 24th, 2026
TRIBECA FESTIVAL AND VULTURE PARTNER TO BRING VULTURE FESTI...
24/03/2026
March 24th, 2026
TRIBECA X ANNOUNCES PRELIMINARY 2026 SPEAKER LINEUP
Cedric the Entertainer, Ted Danson, Brooklyn Peltz Beckham, Dhar Mann, K-Pop Demon ...
24/03/2026
Back to All News
McDonalds and Netflix Call on Fans to Pick a Side With Two New...
24/03/2026
Back to All News
BTS Commands the Global Stage as BTS THE COMEBACK LIVE | ARIRA...
24/03/2026
Artificial intelligence has rapidly emerged as one of the most critical workload...
23/03/2026
The Professional Fighters League (PFL) has renewed its multi-year partnership wi...
23/03/2026
The Snow League has named Google Cloud as its Official Cloud and AI Partner. The...
23/03/2026
Chyron has appointed Eric Wolff as Director of Venues Sales, North America. Wolff previously served as Director of Broadcast Operations & Media Production for T...