Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

ffs non stop stuttering is back anyone had this issue? games unplayable for me right before IEM sydney😪 CPU AMD ryzen 9 5900x and GPU NVIDIA geforce RTX 2080 Ti. Stutters on main menu also

Simon

4,330 subscribers

118,664 Aufrufe • vor 3 Jahren •via X (Twitter)

Wissenschaft & Technologie Gaming

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Oli Tierney

Oli Tierneyvor 3 Jahren

Just wanted to let you know I've never had this issue and I dont know how to help you. Cheers mate, good luck.

Profilbild von Simon

Simonvor 3 Jahren

Hahaha u prick

Profilbild von ropz

ropzvor 3 Jahren

ripbozo

Profilbild von ESL Counter-Strike

ESL Counter-Strikevor 3 Jahren

We spoke to our chief of stuttering science counter-strike viceroy and there is no fix. jks, can someone pls help Simon? @fREQUENCYCS @ThourCS

Profilbild von Merks

Merksvor 3 Jahren

Hey I'd be happy to take a look if you'd like

Profilbild von ESL Counter-Strike

ESL Counter-Strikevor 3 Jahren

@sico_csgo vouch

Profilbild von TjP

TjPvor 3 Jahren

Unfortunate go next :)

Profilbild von MacMate 🇪🇺

MacMate 🇪🇺vor 3 Jahren

This video from @NartOutHere might be able to help you brother. It fixed a bunch of my issues.

Profilbild von Chris JJ Magnum

Chris JJ Magnumvor 3 Jahren

try this video bro

Profilbild von Skirmy 😼

Skirmy 😼vor 3 Jahren

possible GPU issue? Im rocking a 3060 Ti with 5900X and have no stuttering issues at all

Profilbild von Simon

Simonvor 3 Jahren

yeah 2080ti could be doggy for cs2, guess it's pretty old now?

Ähnliche Videos

Featuring either an Intel® Core™ Ultra 9 processor 285K or an AMD Ryzen™ 7 9800X3D processor, and NVIDIA® GeForce RTX™ 5090 GPU, the ROG G700 is built for high-performance gaming. ✅64GB of RAM ✅Tool-less access ✅Optimized airflow

Featuring either an Intel® Core™ Ultra 9 processor 285K or an AMD Ryzen™ 7 9800X3D processor, and NVIDIA® GeForce RTX™ 5090 GPU, the ROG G700 is built for high-performance gaming. ✅64GB of RAM ✅Tool-less access ✅Optimized airflow

ROG Global

39,671 Aufrufe • vor 1 Jahr

Gaming on-the-go is a breeze with the ROG Flow X13. This lightweight gaming laptop packs up to an AMD Ryzen 9 7940HS processor and NVIDIA GeForce RTX 4070 graphics in a sleek chassis. Check it out👉

Gaming on-the-go is a breeze with the ROG Flow X13. This lightweight gaming laptop packs up to an AMD Ryzen 9 7940HS processor and NVIDIA GeForce RTX 4070 graphics in a sleek chassis. Check it out👉

ROG Global

42,646 Aufrufe • vor 3 Jahren

Currently very focused on improving the rig of my new model. For the most part the mesh is "final", just need to finalize the main bone rig and I have to UV map. This is why I missed stream today, also expecting new CPU (AMD Ryzen 9 9950 x3D) for more cores soon.

Currently very focused on improving the rig of my new model. For the most part the mesh is "final", just need to finalize the main bone rig and I have to UV map. This is why I missed stream today, also expecting new CPU (AMD Ryzen 9 9950 x3D) for more cores soon.

❄️Kana Fuyuko❄️

22,438 Aufrufe • vor 8 Monaten

Game Optimizer (CPU Threads Optimizing) - v0.2.0 release v0.2.0 Patch Note: Auto-detect either Windows Game Mode / AMD 3D-V Cache Service is ON, with built wizard to turn off. Add Stop AMD's 3D V-Cache optimizer in General (Turn ON would conflict/crash applications) Improve Frame Drop issue caused by background tasks (Chrome, Firefox, Youtube etc.) Open-source: Please turn off Turbo Game Mode, optimize CCD Parking service in BIOS. Game Mode and AMD's 3D V-Cache optimizer in Windows OS. Test : Overwatch (AMD 9950x3D 16 cores 32 threads) - Auto-Pin to CPU 1% limit throttle All Cores Overwatch(~190 fps) + Multiple Background Apps vs Cache Cores Overwatch(~350 fps) + Freq Cores Background Apps (OBS Studio + Firefox + N.Broadcast etc.) Auto-detect heavy-app turn into Freq mode (Customize CPU% limit throttle) Work CPU models: Intel hybrid (P/E cores) Core Ultra 9 285K, Ultra 7 265K, Ultra 5 245K — Arrow Lake-S Core i9-14900K, i7-14700K, i5-14600K, i5-14400F — Raptor Lake Refresh Core i9-13900K, i7-13700K, i5-13600K — Raptor Lake Core i9-12900K, i7-12700K, i5-12600K — Alder Lake AMD asymmetric cache (X3D): Ryzen 9 9950X3D Ryzen 9 9900X3D Ryzen 9 7950X3D, 7900X3D Multi-CCD symmetric: Ryzen 9 9950X, 9900X, PRO 9965, PRO 9955, PRO 9945 Ryzen 9 9950X3D2 Dual Edition Ryzen 9 7950X, 7900X, 7900, PRO 7945 Ryzen 9 5950X, 5900X, 5900XT, 5900, PRO 5945 Ryzen 9 3950X, 3900X and Ryzen 7 3700X, 2700X Single cache domain: Ryzen 7 9700X, 9700F and Ryzen 5 9600X, 9600, 9500F Ryzen 7 7700X, 7700 and Ryzen 5 7600X, 7600, 7500F Ryzen 7 5800X, 5800XT, 5700X and Ryzen 5 5600X, 5600 Ryzen 7 8700G, Ryzen 5 8600G — monolithic APUs Single-chiplet X3D parts: 9800X3D, 9850X3D, 7800X3D, 5800X3D, 5700X3D, 5600X3D Intel parts without E-cores: i5-12400, i3-12100, i3-13100, i3-14100, i9-9900K, i7-9700K, i5-9600K, i7-2600K Please share results with other CPUs Next Patch Forecast: Customize Cores Slots Profile, now you still could use ALL / ALL no-SMT as cores profile to isolate your game and background app. #IRP_HongKong

IRP_HongKong

91,762 Aufrufe • vor 1 Monat

AMD is entering the humanoid robot “brain” market. At Advancing AI, it launched the Ryzen AI Embedded X100, a Kria platform that unifies CPU/GPU/NPU/FPGA, an open ROCm + ROS 2 stack, and a new Robotics Partner Network. Foundation’s Phantom is the first partner. Its MK-1 has reportedly been tested on the battlefield in Ukraine. The upcoming MK-2 will use X100 for perception and reasoning, with FPGAs handling real-time control of the 23-DoF hands and high-frequency tactile feedback. AMD claims 2.5× faster inference and 3× faster training vs current NVIDIA options. Italian startup Generative Bionics is also using AMD silicon for its GENE.01, emphasizing “body-as-compute.” Most major humanoid players remain with NVIDIA. AMD is betting on openness and FPGA strengths in deterministic control. Meanwhile,In China, UBTECH and MetaX (Muxi) have formed a joint venture to develop dedicated humanoid robot chips, aiming to reduce reliance on NVIDIA, AMD and other international suppliers. The race for physical AI silicon is heating up.

AMD is entering the humanoid robot “brain” market. At Advancing AI, it launched the Ryzen AI Embedded X100, a Kria platform that unifies CPU/GPU/NPU/FPGA, an open ROCm + ROS 2 stack, and a new Robotics Partner Network. Foundation’s Phantom is the first partner. Its MK-1 has reportedly been tested on the battlefield in Ukraine. The upcoming MK-2 will use X100 for perception and reasoning, with FPGAs handling real-time control of the 23-DoF hands and high-frequency tactile feedback. AMD claims 2.5× faster inference and 3× faster training vs current NVIDIA options. Italian startup Generative Bionics is also using AMD silicon for its GENE.01, emphasizing “body-as-compute.” Most major humanoid players remain with NVIDIA. AMD is betting on openness and FPGA strengths in deterministic control. Meanwhile,In China, UBTECH and MetaX (Muxi) have formed a joint venture to develop dedicated humanoid robot chips, aiming to reduce reliance on NVIDIA, AMD and other international suppliers. The race for physical AI silicon is heating up.

CyberRobo

12,774 Aufrufe • vor 2 Monaten

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

Mike

16,097 Aufrufe • vor 4 Monaten

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

AMD CEO LISA SU HELD A MINI PC ON STAGE THAT RUNS A 235B MODEL AND REPLACES YOUR $440/MONTH AI STACK amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on one piece of silicon. cpu and gpu share 128gb of unified memory, no separate graphics card needed the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months install ollama, pull the model, point claude code at localhost. same interface, nothing leaves the machine, nothing costs per request bookmark this and read the article below

starmex

981,931 Aufrufe • vor 4 Monaten

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

PowerInfer - a high-speed inference engine for deploying LLMs locally. Just came across this super interesting project on speeding up inference. It's not MoE but it's a simple approach that exploits the high locality in LLM inference to design a GPU-CPU hybrid inference engine. Hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons (the majority) are computed on the CPU. This approach significantly reduces GPU memory demands and CPU-GPU data transfer. It achieves an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs on a single NVIDIA RTX 4090 GPU. It's on only 18% lower than that achieved by a top-tier server-grade A100 GPU. It also significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy. There is a lot more innovation around inference that's coming fast. Really encouraged by the study on sparse computation to enhance the computational efficiency of LLMs. It's now possible to use PowerInfer with Llama 2 and Faclon 40B. Mistral-7B support is coming soon!

elvis

261,756 Aufrufe • vor 2 Jahren

I really don't post wins much on this app 🤣🤣 it feels good being low-key. Although, let's doxx this one!. Most of the time, I win big, I reinvest, win again, reinvest. I barely spend on myself much, mostly spend my money helping people, or supporting the needy. It's time for me 😌. Hey NVIDIA GeForce Hey ROG Global I Just slapped a Brand new heavy machine in my bag! One of the most powerful laptops of 2025! Emphasis on BRAND NEW! Introducing, the new owner of the ASUS ROG STRIX G16 2025. SPECS: - Intel Core Ultra 9 275HX Processor - 32GB DDR5 RAM - Nvidia GeForce RTX™ 5080 Dedicated GPU with a massive 16GB DDR7 VRAM - 3TB PCIe 4.0 SSD NVME storage - 24 Cores CPU (16 E-cores + 8 P-cores) - Base Frequency 2.70GHz - Max Turbo Frequency 5.40GHz 6 Million Naira well spent on this bad boy. Now, let's lock-in again and run it up back turbo! I need my $U bag soon enough 🤭. Pitch me on to node running, and prover projects, I'm fully locked in.

🐐𝙲𝚛𝚢𝚙𝚝𝚘𝙳𝚛𝚊𝚐𝚘𝚗

20,496 Aufrufe • vor 1 Jahr

CM Punk on main eventing Wrestlemania 41 night 1 “Bret grabbed me right before I went out and had some words for me. Then Taker, bless his heart, brings the mood… Like just snapped me right back into it bc he grabbed me and he went well… Don’t f*** this up.” (Complex News)

CM Punk on main eventing Wrestlemania 41 night 1 “Bret grabbed me right before I went out and had some words for me. Then Taker, bless his heart, brings the mood… Like just snapped me right back into it bc he grabbed me and he went well… Don’t f*** this up.” (Complex News)

Vick

152,668 Aufrufe • vor 8 Monaten

Maximize your earnings with VerAI using top-tier hardware! Let’s explore how the AMD Ryzen 9 9950X & Nvidia GeForce RTX 5090 can power your passive income. 🔧Technical Specs: Why This Setup Excels for AI Training 💻Ryzen 9 9950X: 16 cores, 32 threads, up to 5.7 GHz on Zen 5 perfect for parallel processing in AI workloads, speeding up training cycles. 💻RTX 5090: 32 GB GDDR7, DLSS 4, Optical Flow Accelerator handles GPU-intensive tasks like neural network rendering with ease. 💸 Earnings Breakdown: What You Can Earn ✅💰Hardware Costs: Ryzen 9 9950X ($699) + RTX 5090 ($2,499) = $3,198 total. ✅📊Daily Earnings: Share resources 4 hrs/day (50% usage) & earn 966 VER ($65.69 USDC). ✅🗓️Monthly Earnings: ~$1,970.70 USDC passive income with minimal effort! ✅⏳Amortization: Recover your $3,198 in just ~49 days, then keep earning! 🔗Why VerAI? 💵Effortless Income: Use your PC to contribute to AI training no tech expertise needed. 🌱Sustainable Impact: Share idle resources, reduce waste, and support a greener AI future. 💪Join the Movement: Be part of our waitlist with 80K innovators shaping decentralized AI! Let’s shape the future of AI together join us today! 👉 #VerAI #AIForAll #SustainableTech #JoinTheFuture #EarnCrypto #AIAgents #Innovation

Maximize your earnings with VerAI using top-tier hardware! Let’s explore how the AMD Ryzen 9 9950X & Nvidia GeForce RTX 5090 can power your passive income. 🔧Technical Specs: Why This Setup Excels for AI Training 💻Ryzen 9 9950X: 16 cores, 32 threads, up to 5.7 GHz on Zen 5 perfect for parallel processing in AI workloads, speeding up training cycles. 💻RTX 5090: 32 GB GDDR7, DLSS 4, Optical Flow Accelerator handles GPU-intensive tasks like neural network rendering with ease. 💸 Earnings Breakdown: What You Can Earn ✅💰Hardware Costs: Ryzen 9 9950X ($699) + RTX 5090 ($2,499) = $3,198 total. ✅📊Daily Earnings: Share resources 4 hrs/day (50% usage) & earn 966 VER ($65.69 USDC). ✅🗓️Monthly Earnings: ~$1,970.70 USDC passive income with minimal effort! ✅⏳Amortization: Recover your $3,198 in just ~49 days, then keep earning! 🔗Why VerAI? 💵Effortless Income: Use your PC to contribute to AI training no tech expertise needed. 🌱Sustainable Impact: Share idle resources, reduce waste, and support a greener AI future. 💪Join the Movement: Be part of our waitlist with 80K innovators shaping decentralized AI! Let’s shape the future of AI together join us today! 👉 #VerAI #AIForAll #SustainableTech #JoinTheFuture #EarnCrypto #AIAgents #Innovation

VerAi

13,455 Aufrufe • vor 1 Jahr

AMD CEO Lisa Su just killed Nvidia’s $4,000 AI box with a $1,499 lunchbox. She walked on stage, held it in one hand, and ran a 235 billion parameter model live. No data center. No cloud. No rented GPU. The chip inside is something nobody saw coming. AMD’s Ryzen AI Max+ 395 is the first x86 silicon where CPU and GPU share the same 128GB of memory. That single trick lets a desktop run models that used to need a server rack. Out of those 128GB, Linux hands the GPU 110GB to play with. For context, an RTX 5090 gives you 32GB. A 4090 gives you 24. This box gives you more than three times either of them, in a chassis the size of a thick paperback. The benchmark that broke the room: this chip beat an Nvidia RTX 5080 by more than 3x on DeepSeek R1 inference. A $1,499 lunchbox outrunning a $1,000 discrete graphics card on a real AI workload. Nvidia spent a decade convincing the world you needed their hardware for serious AI. AMD just put that on a desk for half the price. Here is what nobody is telling you. A heavy AI user right now pays $200 for Claude Code Max, $200 for ChatGPT Pro, $20 for Cursor, $20 for Gemini. That is $5,280 a year leaving your account. The box pays itself off in 9 months and then runs free for the rest of its life. Install Ollama. Pull Qwen3 235B. Point Claude Code at localhost. Same interface you already use, except now nothing leaves your machine, nothing costs per request, and no company throttles your usage at 3am when you finally have time to build. This is the moment every AI subscription becomes optional. Lawyers stop fearing OpenAI leaks. Developers stop watching the token meter. Founders stop renting H100s for prototypes that never ship because the bill scared them. The first thousand people to figure this out will own the next two years of private AI consulting. Save this, and read the full breakdown article below you are watching the next shift hit before everyone else does.

AMD CEO Lisa Su just killed Nvidia’s $4,000 AI box with a $1,499 lunchbox. She walked on stage, held it in one hand, and ran a 235 billion parameter model live. No data center. No cloud. No rented GPU. The chip inside is something nobody saw coming. AMD’s Ryzen AI Max+ 395 is the first x86 silicon where CPU and GPU share the same 128GB of memory. That single trick lets a desktop run models that used to need a server rack. Out of those 128GB, Linux hands the GPU 110GB to play with. For context, an RTX 5090 gives you 32GB. A 4090 gives you 24. This box gives you more than three times either of them, in a chassis the size of a thick paperback. The benchmark that broke the room: this chip beat an Nvidia RTX 5080 by more than 3x on DeepSeek R1 inference. A $1,499 lunchbox outrunning a $1,000 discrete graphics card on a real AI workload. Nvidia spent a decade convincing the world you needed their hardware for serious AI. AMD just put that on a desk for half the price. Here is what nobody is telling you. A heavy AI user right now pays $200 for Claude Code Max, $200 for ChatGPT Pro, $20 for Cursor, $20 for Gemini. That is $5,280 a year leaving your account. The box pays itself off in 9 months and then runs free for the rest of its life. Install Ollama. Pull Qwen3 235B. Point Claude Code at localhost. Same interface you already use, except now nothing leaves your machine, nothing costs per request, and no company throttles your usage at 3am when you finally have time to build. This is the moment every AI subscription becomes optional. Lawyers stop fearing OpenAI leaks. Developers stop watching the token meter. Founders stop renting H100s for prototypes that never ship because the bill scared them. The first thousand people to figure this out will own the next two years of private AI consulting. Save this, and read the full breakdown article below you are watching the next shift hit before everyone else does.

AdiiX

3,397,603 Aufrufe • vor 4 Monaten

💥 We pushed the limits of desktop performance with X3D. Then we pushed them further. I’ve been testing the new unreleased Ryzen 9 9950X3D2 Dual Edition in the lab firsthand and it is incredible. The world’s first desktop CPU with dual AMD 3D V-Cache delivers 208MB of total on-chip cache, the most we’ve ever built into a Ryzen processor. That’s several times more than most high-end CPUs had just a few years ago. Whether you’re building unreal game worlds or tackling massive content pipelines, this 16-core Zen 5 beast gives you responsiveness and power like never before, all on a consumer AM5 platform. Coming soon: Available starting April 22nd No compromises. No limits. Games. Creation. AI. Unlocked. 🚀

💥 We pushed the limits of desktop performance with X3D. Then we pushed them further. I’ve been testing the new unreleased Ryzen 9 9950X3D2 Dual Edition in the lab firsthand and it is incredible. The world’s first desktop CPU with dual AMD 3D V-Cache delivers 208MB of total on-chip cache, the most we’ve ever built into a Ryzen processor. That’s several times more than most high-end CPUs had just a few years ago. Whether you’re building unreal game worlds or tackling massive content pipelines, this 16-core Zen 5 beast gives you responsiveness and power like never before, all on a consumer AM5 platform. Coming soon: Available starting April 22nd No compromises. No limits. Games. Creation. AI. Unlocked. 🚀

Jack Huynh

477,099 Aufrufe • vor 6 Monaten

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below

NVIDIA'S BIGGEST COMPETITOR AMD BUILT A BOX THAT RUNS A 235B MODEL AND KILLS $200 OPENAI AND $200 CLAUDE CODE FOR $9 A MONTH amd's ryzen ai max+ 395 is the first x86 chip that runs a 200 billion parameter model on a single piece of silicon with 128gb of unified memory the gmktec evo-x2 runs qwen3 235b fully, deepseek v3 comfortably and llama 3.3 70b with headroom. on linux you get 110gb of usable vram out of 128gb amd claimed the chip beat an nvidia rtx 5080 by more than 3x on deepseek r1 inference. a lunchbox sized pc outrunning a $1,000 discrete gpu on a real ai workload a heavy ai user pays $200 for claude code max, $200 for chatgpt pro, $20 for cursor and $20 for gemini. that's $5,280 a year and the box pays itself off in 9 to 10 months ollama installs in one command and claude code points at localhost so nothing leaves the machine and nothing costs per request bookmark this and read the article below

starmex

93,580 Aufrufe • vor 4 Monaten

$INTC Lip-Bu Tan admits Intel can fill only half its CPU orders and apologizes when CEOs call him "Yeah, I think inferencing is very important. When you want to drive some of this reinforced learning, and also in terms of agentic AI, CPU is the best." "GPU is very good for training, but CPU is really good for orchestration, control plane, and driving some of this even single thread rather than multi-thread has become very useful." "It happened that I invest quite a few companies in the frontier model. They all tell me that, 'Lip-Bu, we need more CPU.'" "So good news is, right now, sometimes in life you need some help. And so the help that come to me is that CPU is so high demand, I only can provide 50% of what the customer want. So many CEO call me up, I had to apologize, I'm not manufacturing enough for them."

$INTC Lip-Bu Tan admits Intel can fill only half its CPU orders and apologizes when CEOs call him "Yeah, I think inferencing is very important. When you want to drive some of this reinforced learning, and also in terms of agentic AI, CPU is the best." "GPU is very good for training, but CPU is really good for orchestration, control plane, and driving some of this even single thread rather than multi-thread has become very useful." "It happened that I invest quite a few companies in the frontier model. They all tell me that, 'Lip-Bu, we need more CPU.'" "So good news is, right now, sometimes in life you need some help. And so the help that come to me is that CPU is so high demand, I only can provide 50% of what the customer want. So many CEO call me up, I had to apologize, I'm not manufacturing enough for them."

Fireside Alpha

142,853 Aufrufe • vor 27 Tagen

.NVIDIA AI kindly sent me a DGX Spark! As soon as I got back from SF, I unboxed it and wanted to share a first look with you. It measures just 15 × 15 × 5.05 cm and weighs 1.2 kg. Inside: • NVIDIA GB10 Grace Blackwell Superchip • 128 GB of unified memory shared by the CPU and GPU • Up to 1 petaflop of theoretical AI compute at FP4 precision with sparsity According to NVIDIA, this little machine can run models with up to 200 billion parameters locally with suitable quantization, and fine-tune models with up to 70 billion parameters using memory-efficient methods such as QLoRA. You can use it to fine-tune models on your own data, customize image generation, and build AI assistants that run locally. I’m looking forward to trying some of those workflows myself. Thanks again to the NVIDIA team for sending this over (NVIDIA RTX Spark)! Once I’m back home, I’ll record some hands-on demos of interesting use cases and share what I learn with you.

.NVIDIA AI kindly sent me a DGX Spark! As soon as I got back from SF, I unboxed it and wanted to share a first look with you. It measures just 15 × 15 × 5.05 cm and weighs 1.2 kg. Inside: • NVIDIA GB10 Grace Blackwell Superchip • 128 GB of unified memory shared by the CPU and GPU • Up to 1 petaflop of theoretical AI compute at FP4 precision with sparsity According to NVIDIA, this little machine can run models with up to 200 billion parameters locally with suitable quantization, and fine-tune models with up to 70 billion parameters using memory-efficient methods such as QLoRA. You can use it to fine-tune models on your own data, customize image generation, and build AI assistants that run locally. I’m looking forward to trying some of those workflows myself. Thanks again to the NVIDIA team for sending this over (NVIDIA RTX Spark)! Once I’m back home, I’ll record some hands-on demos of interesting use cases and share what I learn with you.

Chubby♨️

130,502 Aufrufe • vor 21 Tagen

The official release of Once Human is set for July 9th, 2024 (Pacific Time)! To celebrate, we're hosting a giveaway! ┉┉▾Giveaway▾┉┉ Follow Once Human and repost this post to join. • Event period: Before 23:59 June 17th PT. • Basic Rewards: - Steam Deck 1 TB OLED×1 - Steam Gift Card: $100×5 - Steam Gift Card: $50×10 And that's not all! If any of the following milestones are hit, the prizes get even better! • Giveaway Upgrades: - Reach 3,000 engagements (likes, comments, reposts): + Steam Deck×1 - Reach 50,000 followers: + Steam Decks×1 - During Steam Next Fest, if Once Human reaches Steam's "Most Played" Top 10: + AMD×Once Human limited co-branded host [AMD Radeon™ RX 7900 Series GPU, AMD Ryzen™ 9 7800X3D CPU] ×1 Don't forget to wishlist now and pre-download our Steam Next Fest demo starting June 7th. Get ready to start playing at 10:00 AM on June 10th PT! Wishlist on Steam: #OnceHuman

The official release of Once Human is set for July 9th, 2024 (Pacific Time)! To celebrate, we're hosting a giveaway! ┉┉▾Giveaway▾┉┉ Follow Once Human and repost this post to join. • Event period: Before 23:59 June 17th PT. • Basic Rewards: - Steam Deck 1 TB OLED×1 - Steam Gift Card: $100×5 - Steam Gift Card: $50×10 And that's not all! If any of the following milestones are hit, the prizes get even better! • Giveaway Upgrades: - Reach 3,000 engagements (likes, comments, reposts): + Steam Deck×1 - Reach 50,000 followers: + Steam Decks×1 - During Steam Next Fest, if Once Human reaches Steam's "Most Played" Top 10: + AMD×Once Human limited co-branded host [AMD Radeon™ RX 7900 Series GPU, AMD Ryzen™ 9 7800X3D CPU] ×1 Don't forget to wishlist now and pre-download our Steam Next Fest demo starting June 7th. Get ready to start playing at 10:00 AM on June 10th PT! Wishlist on Steam: #OnceHuman

Once Human

1,834,002 Aufrufe • vor 2 Jahren