Loading video...

Video Failed to Load

Go Home

The exact NVIDIA optimization order I follow on every PC I optimize. Clean driver. GPU-Z check. NVIDIA App settings. Most people skip step two and wonder why their GPU is running slow. Full guide here.

x1lly's profile picture

Xilly

24,790 subscribers

14,004 views • 14 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

PC Users🚨 If you update your NVIDIA and AMD GPU Drivers via the Apps, you’re Killing your Gaming Performance on Windows This is the BEST way to Update/Reinstall Drivers to Improve FPS and Lower Latency Nvidia Control Panel Settings Included! PTU👇
3:45

PC Users🚨 If you update your NVIDIA and AMD GPU Drivers via the Apps, you’re Killing your Gaming Performance on Windows This is the BEST way to Update/Reinstall Drivers to Improve FPS and Lower Latency Nvidia Control Panel Settings Included! PTU👇

Paragon│Boost Gaming PC Performance

1,082,548 views • 4 months ago

I don't know what I expected but Linux gaming just works at this point. I'm on a fresh install of Fedora 44 on an NVIDIA GPU and everything just works. What's going on? Is 2026 really the year of Linux?
0:34

I don't know what I expected but Linux gaming just works at this point. I'm on a fresh install of Fedora 44 on an NVIDIA GPU and everything just works. What's going on? Is 2026 really the year of Linux?

FR3NKD

72,922 views • 3 months ago

YOUR PARENTS PAID FOR THE CUDA MOAT! The #1 contributor to the CUDA MOAT isn't the the developers at NVIDIA, but it is the millions of developers outside of NVIDIA that invent new algorithms for CUDA like Flash Attention. For most of them, it started with an GeForce gaming GPU. NVIDIA is the only companies that has an reasonable good developer stack on consumer grade GPUs. As people grow up beyond playing CSGO & League of Legends & Minecraft, they either become anime weeaboos or they start programming on their existing computer with has an GeForce GPU
0:23

YOUR PARENTS PAID FOR THE CUDA MOAT! The #1 contributor to the CUDA MOAT isn't the the developers at NVIDIA, but it is the millions of developers outside of NVIDIA that invent new algorithms for CUDA like Flash Attention. For most of them, it started with an GeForce gaming GPU. NVIDIA is the only companies that has an reasonable good developer stack on consumer grade GPUs. As people grow up beyond playing CSGO & League of Legends & Minecraft, they either become anime weeaboos or they start programming on their existing computer with has an GeForce GPU

SemiAnalysis

25,230 views • 4 months ago

Here is Ternary Bonsai 27B running an end-to-end agentic workflow locally with Hermes on an NVIDIA GeForce RTX 5090 GPU. The model reasons, calls tools, reads outputs, modifies files, and surfaces insights - all on consumer hardware, while all private files, intermediate states, and iterations remain local.
1:46

Here is Ternary Bonsai 27B running an end-to-end agentic workflow locally with Hermes on an NVIDIA GeForce RTX 5090 GPU. The model reasons, calls tools, reads outputs, modifies files, and surfaces insights - all on consumer hardware, while all private files, intermediate states, and iterations remain local.

PrismML

153,244 views • 25 days ago

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.
2:48

It's here: We just hit superhuman performance on AI kernel optimization! Real customer models & production settings. Not toy problems (what I typically see). This is the year that Claude writes its own kernels, Codex its own kernels, for every new GPU that it wants to run on -- something that takes months to port between GPU generations today. This has a massive impact to scaling intelligence. More compute means getting the next frontier model sooner.

Sharon Zhou

241,935 views • 5 months ago

NVIDIA CEO, Jensen Huang: "Nobody writes prompts anymore. The new job is building Loops and Graphs." In 50 minutes he explains why the engineers who stopped prompting are already years ahead, and what they're building instead. The missing piece most people skip: loops handle the work, graphs handle the loops. Watch it, then read the full guide on loops and graphs below.
48:05

NVIDIA CEO, Jensen Huang: "Nobody writes prompts anymore. The new job is building Loops and Graphs." In 50 minutes he explains why the engineers who stopped prompting are already years ahead, and what they're building instead. The missing piece most people skip: loops handle the work, graphs handle the loops. Watch it, then read the full guide on loops and graphs below.

Mahax

1,068,549 views • 1 day ago

llama3 8B (not quantized) running on an heterogeneous home cluster made of: - iPhone 15 Pro Max - iPad Pro (not sure which version XD) - MacBook Pro ( M1 Max ) - NVIDIA GeForce 3080 (not visible in video) - 2x NVIDIA Titan X Pascal Very soon also supporting Android (I *have* to also add my NVIDIA Shield GPU!!!!!). Single code base, single model format (reduced and optimally distributed to every node to save space). Everything (including iOS code) is open here ... it would be really nice, with the help of the community, taking this project to the next level in terms of optimization and support. My vision is about a distributed inference server that can run any model on any backend in any cluster topology - let's fight programmed obsolescence and democratize inference!
0:26

llama3 8B (not quantized) running on an heterogeneous home cluster made of: - iPhone 15 Pro Max - iPad Pro (not sure which version XD) - MacBook Pro ( M1 Max ) - NVIDIA GeForce 3080 (not visible in video) - 2x NVIDIA Titan X Pascal Very soon also supporting Android (I *have* to also add my NVIDIA Shield GPU!!!!!). Single code base, single model format (reduced and optimally distributed to every node to save space). Everything (including iOS code) is open here ... it would be really nice, with the help of the community, taking this project to the next level in terms of optimization and support. My vision is about a distributed inference server that can run any model on any backend in any cluster topology - let's fight programmed obsolescence and democratize inference!

Simone Margaritelli

304,072 views • 2 years ago

Windows ML is now generally available! This milestone brings powerful, local AI capability to every Windows 11 device, harnessing the full power of the GPU, NPU, and CPU. Big thank you to the team and our silicon partners, AMD, Intel, NVIDIA, and Qualcomm, for their collaboration to unlock real-time, secure, and efficient AI experiences for developers on Windows. Let’s go 🚀!
1:16

Windows ML is now generally available! This milestone brings powerful, local AI capability to every Windows 11 device, harnessing the full power of the GPU, NPU, and CPU. Big thank you to the team and our silicon partners, AMD, Intel, NVIDIA, and Qualcomm, for their collaboration to unlock real-time, secure, and efficient AI experiences for developers on Windows. Let’s go 🚀!

Pavan Davuluri

11,663 views • 10 months ago

Jensen Huang, CEO of Nvidia: "In a few years every engineer is going to have and manage hundreds of AI agents" 15 minutes from the man whose chips run every AI system on the planet he's not predicting the future, he's describing what's already happening inside Nvidia right now most people have no idea how far behind they actually are with AI that's exactly why I wrote an article on Claude features most people don't even know exist read the article below and you'll already be ahead of 99% of people
15:23

Jensen Huang, CEO of Nvidia: "In a few years every engineer is going to have and manage hundreds of AI agents" 15 minutes from the man whose chips run every AI system on the planet he's not predicting the future, he's describing what's already happening inside Nvidia right now most people have no idea how far behind they actually are with AI that's exactly why I wrote an article on Claude features most people don't even know exist read the article below and you'll already be ahead of 99% of people

Anatoli Kopadze

49,978 views • 2 months ago

I don’t know why people say Wuthering Waves is so unoptimized. I’m running the game on a mid-range PC, and it’s running perfectly fine.. #WutheringWaves
1:02

I don’t know why people say Wuthering Waves is so unoptimized. I’m running the game on a mid-range PC, and it’s running perfectly fine.. #WutheringWaves

Kaito

58,156 views • 4 months ago

I sat down with NVIDIA Sam Stanwyck (Sam Stanwyck) at ISC to talk about one of the most misunderstood areas in computing: quantum. We discussed why NVIDIA is not building a quantum computer, but instead the infrastructure around it: GPUs, AI, CUDA-Q, quantum simulation, control systems, error correction, and the path toward hybrid CPU/GPU/QPU supercomputing. The key takeaway: Quantum will likely not arrive as a standalone magic machine. It will arrive as part of a much larger accelerated computing stack, combining classical supercomputers, AI, GPUs, and quantum processors to tackle problems in chemistry, materials science, energy, optimization, and fundamental science. Full episode with Sam Stanwyck is now live.
19:36

I sat down with NVIDIA Sam Stanwyck (Sam Stanwyck) at ISC to talk about one of the most misunderstood areas in computing: quantum. We discussed why NVIDIA is not building a quantum computer, but instead the infrastructure around it: GPUs, AI, CUDA-Q, quantum simulation, control systems, error correction, and the path toward hybrid CPU/GPU/QPU supercomputing. The key takeaway: Quantum will likely not arrive as a standalone magic machine. It will arrive as part of a much larger accelerated computing stack, combining classical supercomputers, AI, GPUs, and quantum processors to tackle problems in chemistry, materials science, energy, optimization, and fundamental science. Full episode with Sam Stanwyck is now live.

Chubby♨️

22,673 views • 1 month ago

Jensen is using Nebius to fight the hyperscalers and this is why they will be a $1T hyperscaler (Save this) According to a new Schedule 13G filing, Nvidia beneficially owns 22.25 million Class A shares of Nebius, made up of 1.19 million shares held directly and 21.07 million shares tied to pre-funded warrants acquired back in March 2026. That warrant stake traces back to a $2 billion deal Nvidia struck with Nebius on March where Nvidia bought pre-funded warrants for roughly 21 million shares at an exercise price of essentially zero, structured to work almost like an upfront equity check. Nvidia is currently restricted from exercising or selling any of those warrant-backed shares until September 11, 2026, so this stake has been locked up and largely out of the news cycle until the filing just brought it back into view. That deal came bundled with a much bigger strategic partnership. Alongside the investment, Nvidia and Nebius announced a plan to build out more than 5 gigawatts of Nvidia-powered AI cloud infrastructure by the end of 2030, giving Nebius early access to Nvidia's next-generation Rubin platform, Vera CPUs, and BlueField storage systems well ahead of most competitors. This stake fits a pattern Jensen Huang has been running for a while now. Huang reportedly hates a world where hyperscalers control all the compute, since Google TPUs and Amazon Trainium getting stronger is the one outcome that actually threatens Nvidia long-term. That's why Nvidia keeps putting money into neoclouds like Nebius and CoreWeave and backstopping their GPU clusters, effectively betting on a wide field of players rather than letting three or four hyperscalers dominate the entire compute layer. A GPU sold to Nebius costs Nvidia the same as a GPU sold to Google today, but five years out, every neocloud that survives and scales is one more customer that isn't building its own competing chip and one more reason inference keeps running on open, non-hyperscaler infrastructure instead of a closed ecosystem Nvidia doesn't control. That's the real bull case for Nebius becoming a trillion dollar hyperscaler in its own right. It already has $27 billion locked in from Meta, $17.3 billion from Microsoft, direct equity backing from Nvidia and priority access to Nvidia's next generation chip roadmap before most competitors get it, giving it the capital, the customer base, and the hardware edge all at once, exactly the combination Nvidia needs someone to have if it wants a real fifth hyperscaler standing up against Google, Amazon, Microsoft, and Meta. I remain extremely bullish on Nebius, follow me Melvin for more infrastructure plays and make sure to check out the link below for more!
2:12

Jensen is using Nebius to fight the hyperscalers and this is why they will be a $1T hyperscaler (Save this) According to a new Schedule 13G filing, Nvidia beneficially owns 22.25 million Class A shares of Nebius, made up of 1.19 million shares held directly and 21.07 million shares tied to pre-funded warrants acquired back in March 2026. That warrant stake traces back to a $2 billion deal Nvidia struck with Nebius on March where Nvidia bought pre-funded warrants for roughly 21 million shares at an exercise price of essentially zero, structured to work almost like an upfront equity check. Nvidia is currently restricted from exercising or selling any of those warrant-backed shares until September 11, 2026, so this stake has been locked up and largely out of the news cycle until the filing just brought it back into view. That deal came bundled with a much bigger strategic partnership. Alongside the investment, Nvidia and Nebius announced a plan to build out more than 5 gigawatts of Nvidia-powered AI cloud infrastructure by the end of 2030, giving Nebius early access to Nvidia's next-generation Rubin platform, Vera CPUs, and BlueField storage systems well ahead of most competitors. This stake fits a pattern Jensen Huang has been running for a while now. Huang reportedly hates a world where hyperscalers control all the compute, since Google TPUs and Amazon Trainium getting stronger is the one outcome that actually threatens Nvidia long-term. That's why Nvidia keeps putting money into neoclouds like Nebius and CoreWeave and backstopping their GPU clusters, effectively betting on a wide field of players rather than letting three or four hyperscalers dominate the entire compute layer. A GPU sold to Nebius costs Nvidia the same as a GPU sold to Google today, but five years out, every neocloud that survives and scales is one more customer that isn't building its own competing chip and one more reason inference keeps running on open, non-hyperscaler infrastructure instead of a closed ecosystem Nvidia doesn't control. That's the real bull case for Nebius becoming a trillion dollar hyperscaler in its own right. It already has $27 billion locked in from Meta, $17.3 billion from Microsoft, direct equity backing from Nvidia and priority access to Nvidia's next generation chip roadmap before most competitors get it, giving it the capital, the customer base, and the hardware edge all at once, exactly the combination Nvidia needs someone to have if it wants a real fifth hyperscaler standing up against Google, Amazon, Microsoft, and Meta. I remain extremely bullish on Nebius, follow me Melvin for more infrastructure plays and make sure to check out the link below for more!

Melvin

75,069 views • 19 days ago

Jensen Huang says NVIDIA doesn't actually build computers — and that's why every investor can't wait for them. "We don't build computers," Huang says. "We actually don't build clouds." "As it turns out, we're a computing platform company. And nobody can buy anything from us." "We vertically design, vertically integrate to design and optimize. But then we open up the entire platform at every single layer to be integrated into other companies' products." "I can't do what I do without having convinced them first." "Most of GTC is about manifesting a future that by the time my product is ready, they're going, 'What took you so long?'" Three layers, three owners: - NVIDIA owns the design - The supply chain owns the manufacturing - The clouds own the customers Huang owns the future they're all building together. P.S. I made a playbook breaking down 100+ most powerful decision making mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Grab a free copy here: If you're new here, follow GeniusThinking for content on the greatest minds in economics, psychology, and history. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast
0:46

Jensen Huang says NVIDIA doesn't actually build computers — and that's why every investor can't wait for them. "We don't build computers," Huang says. "We actually don't build clouds." "As it turns out, we're a computing platform company. And nobody can buy anything from us." "We vertically design, vertically integrate to design and optimize. But then we open up the entire platform at every single layer to be integrated into other companies' products." "I can't do what I do without having convinced them first." "Most of GTC is about manifesting a future that by the time my product is ready, they're going, 'What took you so long?'" Three layers, three owners: - NVIDIA owns the design - The supply chain owns the manufacturing - The clouds own the customers Huang owns the future they're all building together. P.S. I made a playbook breaking down 100+ most powerful decision making mental models used by history's greatest thinkers. 5,000+ downloads. 113 five-star reviews. Grab a free copy here: If you're new here, follow GeniusThinking for content on the greatest minds in economics, psychology, and history. — Jensen Huang ( NVIDIA ), NVIDIA CEO, on Lex Fridman's ( Lex Fridman ) podcast

GeniusThinking

37,751 views • 1 month ago

🚨🚨If you are playing the Battlefield 6 Beta, watch this video to make sure your pc is ready to go.🚨🚨 -Game settings -secure boot/ how to find -controller overclock WITH secure boot enabled. -updating to newest gpu drivers/ nvcp settings RT To save a friend People with bugs/ issues reply below and I will help everyone that I can.
6:37

🚨🚨If you are playing the Battlefield 6 Beta, watch this video to make sure your pc is ready to go.🚨🚨 -Game settings -secure boot/ how to find -controller overclock WITH secure boot enabled. -updating to newest gpu drivers/ nvcp settings RT To save a friend People with bugs/ issues reply below and I will help everyone that I can.

Kibbs

89,766 views • 1 year ago

🚨 I warned everyone about $NVDA… and people were pissed. On November 19, 2024, I said the last two times this happened to $NVDA, it dumped 20%. I said, "Don’t shoot the messenger—I hope I’m wrong." That video got 108,000 views, and the comments were filled with people saying I was crazy. Now? Nvidia is down 20.9%. In this video, I break down: 📉 Why we knew this sell-off was coming 🔍 The key levels Nvidia MUST hold ⚠️ How low it could go if support breaks
4:24

🚨 I warned everyone about $NVDA… and people were pissed. On November 19, 2024, I said the last two times this happened to $NVDA, it dumped 20%. I said, "Don’t shoot the messenger—I hope I’m wrong." That video got 108,000 views, and the comments were filled with people saying I was crazy. Now? Nvidia is down 20.9%. In this video, I break down: 📉 Why we knew this sell-off was coming 🔍 The key levels Nvidia MUST hold ⚠️ How low it could go if support breaks

Peter DiCarlo

54,614 views • 1 year ago

We are excited to share a deeper look into the GPU Sharing Platform that will power AI applications on the InfraX V4 DApp. In this demo we showcase a GPU running and completing an image generation task. Our backend successfully leverages this GPU (and CPU) in real time to complete the job, earning the user money, and powering the infraX platform. Here’s how it works 👉 when you connect to the InfraX DApp, our platform automatically detects the GPU on your machine and immediately checks it eligibility and where it can be used. From there, each user dictates exactly how and when they want to contribute their GPU power by setting the days their PC is most available (throughout the night, for example). Additional, each user will be able to pause their GPU's connection to infraX whenever they need to use it locally, resuming with a just a single click. Once activated, your GPU seamlessly plugs into the InfraX network and begins fulfilling compute jobs, earning YOU money. Go on, take the $INFRA pill..
1:14

We are excited to share a deeper look into the GPU Sharing Platform that will power AI applications on the InfraX V4 DApp. In this demo we showcase a GPU running and completing an image generation task. Our backend successfully leverages this GPU (and CPU) in real time to complete the job, earning the user money, and powering the infraX platform. Here’s how it works 👉 when you connect to the InfraX DApp, our platform automatically detects the GPU on your machine and immediately checks it eligibility and where it can be used. From there, each user dictates exactly how and when they want to contribute their GPU power by setting the days their PC is most available (throughout the night, for example). Additional, each user will be able to pause their GPU's connection to infraX whenever they need to use it locally, resuming with a just a single click. Once activated, your GPU seamlessly plugs into the InfraX network and begins fulfilling compute jobs, earning YOU money. Go on, take the $INFRA pill..

infraX | $INFRA

30,615 views • 11 months ago

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."
2:00

Dylan Patel of SemiAnalysis says a worse GPU with better storage and memory now beats the best chip without them, so buying the newest GPU alone no longer wins inference. So, an AMD GPU with more memory can outperform Nvidia in some cases. "So what we have is we have over $80 million of compute, GPUs from Nvidia, AMD, TPUs from Google, Trainium from Amazon, and we run this benchmark constantly on the newest inference engine, newest drivers, newest PyTorch version, whatever it is." "Every day it runs on an automated CI, and we run it on all the latest Chinese models, from GLM, Zhipu, Moonshot, Kimi, Alibaba, all these models we run." "Initially, when we were benchmarking the difference between these chips and different engines, different schemes for parallelism, we were just running it fixed context length." "But now with Agent X, we've analyzed over $5 million worth of Claude Code traces. This is real production traffic that people have donated to us as well as internally generated. Now we know what the actual agent workload looks like." "And then as we implement that and run those benchmarks, it turns out yes, the chip you're using is very important, but now even more important is how are you handling this memory offload?" "And so while an Nvidia GPU is faster than an AMD GPU in most cases, because AMD GPUs have more memory, they actually end up outperforming in some cases." "Or you can have a worse GPU, but a much better storage solution, and now you can outperform what the best GPU can do without those solutions. So just buying the newest and latest GPU alone doesn't get you the best inference economics." "Actually, you need to layer in all these other innovations including storage and memory." [ Who's the top player on your chart? ] "That really is a difficult multivariable problem. And generally that means you need to have, yes, you need to have the best GPU, a GB300, but you also need to have the best storage solutions. And so I won't spoil who's the best right here, but I will say that storage solutions matter a lot and memory solutions matter a lot, as does your front-end networking. That matters a lot."

Fireside Alpha

175,085 views • 13 days ago

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)
0:37

Claude Code is CRACKED at design now and I don't think people understand how BIG this is. There is now one tool that takes you from a rough idea to fully designed, agency-tier, App Store-ready screens in minutes. One design system, every screen, real native code. Most builders hand design to Claude Code, get AI-default screens, and wonder why their app looks like every other vibe coded project. This is the 3-step workflow that fixes it: (full breakdown in the article)

Prajwal Tomar

105,433 views • 1 month ago

Dylan Patel on the importance of memory and storage Two key quotes: "An $NVDA GPU is faster than an $AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads." “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly" Full Quote: “We have over $80 million of compute: GPUs from $NVDA and $AMD, TPUs from Google, and Trainium from Amazon. We constantly run this benchmark using the newest inference engines, drivers, PyTorch versions, and other software. It runs every day through automated CI across the latest Chinese models from GLM, Zhipu, Moonshot, Kimi, Alibaba, and others. Initially, when we were benchmarking the differences between these chips, inference engines, and parallelism schemes, we used fixed context lengths. But with Agent X, we have now analyzed more than $5 million worth of Claude Code traces. This is real production traffic that users have donated to us, combined with internally generated data, so we now understand what an actual agent workload looks like. When we implement those workloads and run the benchmarks, it turns out that the chip you are using is very important, but how you handle memory offload can be even more important. An Nvidia GPU is faster than an AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads. Similarly, you can use a less powerful GPU with a much better storage solution and outperform the best GPU when it lacks those solutions. Simply buying the newest GPU does not necessarily give you the best inference economics. You need to layer in other innovations, including storage and memory.” Interviewer: “Who is the top player on your chart? Can you tell us?” Dylan Patel: “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly.”
2:27

Dylan Patel on the importance of memory and storage Two key quotes: "An $NVDA GPU is faster than an $AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads." “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly" Full Quote: “We have over $80 million of compute: GPUs from $NVDA and $AMD, TPUs from Google, and Trainium from Amazon. We constantly run this benchmark using the newest inference engines, drivers, PyTorch versions, and other software. It runs every day through automated CI across the latest Chinese models from GLM, Zhipu, Moonshot, Kimi, Alibaba, and others. Initially, when we were benchmarking the differences between these chips, inference engines, and parallelism schemes, we used fixed context lengths. But with Agent X, we have now analyzed more than $5 million worth of Claude Code traces. This is real production traffic that users have donated to us, combined with internally generated data, so we now understand what an actual agent workload looks like. When we implement those workloads and run the benchmarks, it turns out that the chip you are using is very important, but how you handle memory offload can be even more important. An Nvidia GPU is faster than an AMD GPU in most cases, but because AMD GPUs have more memory, they can outperform Nvidia in certain workloads. Similarly, you can use a less powerful GPU with a much better storage solution and outperform the best GPU when it lacks those solutions. Simply buying the newest GPU does not necessarily give you the best inference economics. You need to layer in other innovations, including storage and memory.” Interviewer: “Who is the top player on your chart? Can you tell us?” Dylan Patel: “It is a difficult, multivariable problem. Generally, you need the best GPU, such as a GB300, but you also need the best storage solutions. I will not spoil who comes out on top, but storage solutions matter a lot, memory solutions matter a lot, and frontend networking also matters significantly.”

Daniel Romero

38,220 views • 28 days ago