Loading video...

Video Failed to Load

Go Home

Cloud GPU training is a scam. A single M4 MacBook does 2.9 TFLOPS. Seven friends with MacBooks match an NVIDIA A100. Alexander Hayes just open-sourced a tool that makes this work over Wi-Fi. It's called AirTrain. Here's how it works: Traditional distributed training (DDP) syncs gradients after every single...

heygurisingh's profile picture

Guri Singh

53,747 subscribers

160,201 views • 1 month ago •via X (Twitter)

EducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

GPU tradeoff series: A100 is not much more powerful than 4090 🫠 GPU Perf and Price: - 4090: 330 fp16 TFLOPs, $1,749 - A100 (80GB): 312 fp16 TFLOPs, $20,000 > A100 is 11.4X more pricy Training speed for GPT-2(124M) with llm.c: - 4090: 153K tokens/s - A100 (80GB): 195K tokens/s > A100 is only 1.3X faster (both trained using a single card, A100 llm.c training is shown in the video, 4090 video is in the quoted tweet) Conclusion: 4090 has a much better cost vs performance ratio Why: As in the H100 vs. 4090 comparison, the biggest difference between A100 and 4090 is their GPU memory size/bandwidth and cross-GPU communication bandwidth, which does not matter too much if your model can fit into a single 4090. Specs: 4090: - GPU memory size: 24GB - memory bandwidth: 1 TB/s - communication bandwidth: 64 GB/s A100: - GPU memory size: 80GB - memory bandwidth: 2 TB/s - communication bandwidth: 900 GB/s Nvidia killed off NVLink (a high-speed communication link that connects GPUs) on 4090. (Jensen Huang smiling face) If multiple 4090s could be interconnected via NVLink, their performance would be closer to datacenter-grade A100 GPUs, even for training larger models. Additionally, 4090 isn't allowed in datacenters, that's how Nvidia makes 💰💰💰
0:32

GPU tradeoff series: A100 is not much more powerful than 4090 🫠 GPU Perf and Price: - 4090: 330 fp16 TFLOPs, $1,749 - A100 (80GB): 312 fp16 TFLOPs, $20,000 > A100 is 11.4X more pricy Training speed for GPT-2(124M) with llm.c: - 4090: 153K tokens/s - A100 (80GB): 195K tokens/s > A100 is only 1.3X faster (both trained using a single card, A100 llm.c training is shown in the video, 4090 video is in the quoted tweet) Conclusion: 4090 has a much better cost vs performance ratio Why: As in the H100 vs. 4090 comparison, the biggest difference between A100 and 4090 is their GPU memory size/bandwidth and cross-GPU communication bandwidth, which does not matter too much if your model can fit into a single 4090. Specs: 4090: - GPU memory size: 24GB - memory bandwidth: 1 TB/s - communication bandwidth: 64 GB/s A100: - GPU memory size: 80GB - memory bandwidth: 2 TB/s - communication bandwidth: 900 GB/s Nvidia killed off NVLink (a high-speed communication link that connects GPUs) on 4090. (Jensen Huang smiling face) If multiple 4090s could be interconnected via NVLink, their performance would be closer to datacenter-grade A100 GPUs, even for training larger models. Additionally, 4090 isn't allowed in datacenters, that's how Nvidia makes 💰💰💰

Yuchen Jin

234,951 views • 1 year ago

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.
0:20

"Mac Minis for example are a very good fit" - Andrej Karpathy Andrej Karpathy shouted out my work on EXO Labs in his keynote at Y Combinator AI SUS! Here's the breakdown: Right now most AI workloads run in the cloud where requests from different users are continuously batched together. These workloads are FLOPS-bound and favors hardware with the best unit economics of $ per FLOP, i.e. enterprise GPUs. The personal computing revolution will shift these workloads to personal devices with lower batch sizes (mostly batch_size=1). batch_size=1 inference is memory-bound, because all of the model parameters need to be loaded into the GPU every time a token is generated. Apple Silicon with its Unified Memory architecture has a lot of memory and memory bandwidth per $ compared to other hardware: - M4 Pro Mac Mini, 24GB @ 273GB/s, $58.33/GB, $5.13/GB/s - H100, 80GB @ 3350GB/s, $625/GB, $14.93/GB/s The unit economics of Apple Silicon are becoming more compelling with every release of the Mac. The future of AI inference looks more like open weights models (OpenAI open weights model soonTM) run at low batch_size on personal devices.

Alex Cheema

103,487 views • 1 year ago

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:
0:20

The latest MLX has a CUDA back-end! To get started: pip install "mlx[cuda]" With the same codebase you can develop locally, run your model on Apple silicon, or in the cloud on Nvidia GPUs. MLX is designed around Apple silicon - which has a unified memory architecture. It uses the same design with CUDA. So there's no need to move arrays around from CPU memory to GPU memory. Note, this is early days - some operations are missing and performance is still being optimized. But it's already quite fast for Transformer training, text generation, and more! Here's a demo using mlx-lm to generate text with Llama 3 8B (bf16) on an A100:

Awni Hannun

42,751 views • 10 months ago

Jensen Huang said Grok 5 will be 7 Trillion parameter model. On time to train, with the training window fixed at 1 month, the new Vera-Rubin GPU system of Nvidia needs 1/4 the number of systems compared with Blackwell to train the same frontier model. “factory throughput” improves by about 10x over Blackwell, and Blackwell itself was about 10x over Hopper. i.e. overall Rubin is roughly 100x Hopper in factory throughput per watt, which matters hugely, because a 1 GW, $50B data center is power-limited and revenue scales with throughput per watt. --- From Nvidia YT channel
1:24

Jensen Huang said Grok 5 will be 7 Trillion parameter model. On time to train, with the training window fixed at 1 month, the new Vera-Rubin GPU system of Nvidia needs 1/4 the number of systems compared with Blackwell to train the same frontier model. “factory throughput” improves by about 10x over Blackwell, and Blackwell itself was about 10x over Hopper. i.e. overall Rubin is roughly 100x Hopper in factory throughput per watt, which matters hugely, because a 1 GW, $50B data center is power-limited and revenue scales with throughput per watt. --- From Nvidia YT channel

Rohan Paul

165,770 views • 5 months ago

I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵
1:39

I ran a 35-billion parameter AI agent on a $600 Mac mini. Specs: M4 Mac-Mini 16GB RAM The model doesn't fit in RAM. It pages from the SSD at 30 tokens/second. On NVIDIA, the same paging gives you 1.6 tok/s. Apple Silicon gives you 30. That's 18.6x faster. No cloud. No API keys. $0/month. Here's what it can do 🧵

thestreamingdev()

725,284 views • 2 months ago

I trained models across MacBooks using Apple's AirDrop protocol. grove is a distributed training library for Apple Silicon. Devices discover each other over AWDL, a direct radio link. If there's a shared WiFi network it upgrades to that for speed, otherwise everything goes over the direct link. No router, no cloud, no setup. grove start -n 4 grove join
0:34

I trained models across MacBooks using Apple's AirDrop protocol. grove is a distributed training library for Apple Silicon. Devices discover each other over AWDL, a direct radio link. If there's a shared WiFi network it upgrades to that for speed, otherwise everything goes over the direct link. No router, no cloud, no setup. grove start -n 4 grove join

Swarnim Jain

666,255 views • 2 months ago

JENSEN HUANG UNVEILED A $3,000 SUPERCOMPUTER THAT REPLACES $1,900/MONTH IN CLOUD GPUS WITH $2 IN ELECTRICITY. IT FITS ON YOUR DESK a developer was paying $1,900 a month renting a100 and h100 cloud gpus. he bought the dgx spark, set it up in an afternoon, and his monthly bill dropped from $1,900 to $2 in electricity the box runs 128gb of unified memory and 1 petaflop of ai compute. a 4090 gives you 24gb of vram and taps out at 30b models. the spark loads 70b at full precision and stretches to 200b without breaking a sweat break-even hit in 6 weeks. after that the $1,890 he used to wire to a rental company every month stayed in his business. first year that's $22,000 back install ollama, change one line in your code, point it at localhost instead of the cloud. nothing else changes. nothing leaves your machine and nothing costs money per request cloud gpu costs aren't getting cheaper and rate limits keep getting tighter. the people who pulled their ai workloads onto a box on their desk in 2026 are going to look very far ahead in 2028 bookmark this and read the article below
0:33

JENSEN HUANG UNVEILED A $3,000 SUPERCOMPUTER THAT REPLACES $1,900/MONTH IN CLOUD GPUS WITH $2 IN ELECTRICITY. IT FITS ON YOUR DESK a developer was paying $1,900 a month renting a100 and h100 cloud gpus. he bought the dgx spark, set it up in an afternoon, and his monthly bill dropped from $1,900 to $2 in electricity the box runs 128gb of unified memory and 1 petaflop of ai compute. a 4090 gives you 24gb of vram and taps out at 30b models. the spark loads 70b at full precision and stretches to 200b without breaking a sweat break-even hit in 6 weeks. after that the $1,890 he used to wire to a rental company every month stayed in his business. first year that's $22,000 back install ollama, change one line in your code, point it at localhost instead of the cloud. nothing else changes. nothing leaves your machine and nothing costs money per request cloud gpu costs aren't getting cheaper and rate limits keep getting tighter. the people who pulled their ai workloads onto a box on their desk in 2026 are going to look very far ahead in 2028 bookmark this and read the article below

starmex

140,989 views • 16 days ago

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones
1:37

I got Llama 3 running in my browser using only my GPU with my Wi-Fi switched OFF completely client-side WebGPU is a new feature in browsers where JS can use the GPU of the device and apparently you can run LLMs on it too, and it's fast! My end goal for 🧠 is a locally run client side 100% private conversation where nothing gets sent to, processed in or stored in the cloud This will be helpful because I prefer making it web based instead of coding for 4 different native platforms (iOS, Android, MacOS, Windows) Two challenges still: 1) the user has to download the LLM model first and the smallest model is still ~3GB, but they only have to download it once 2) not all devices have fast GPUs yet for LLMs, but it's starting to become a default in most devices e.g.s smartphones

@levelsio

261,352 views • 2 years ago

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.
1:24

NVIDIA just released a new open source transcription model, Nemotron Speech ASR, designed from the ground up for low-latency use cases like voice agents. Here's a voice agent built with this new model. 24ms transcription finalization and total voice-to-voice inference time under 500ms. This agent actually uses *three* NVIDIA open source models: - Nemotron Speech ASR - Nemotron 3 Nano 30GB in a 4-bit quant (released in December) - A preview checkpoint of the upcoming Magpie text-to-speech model These models are all truly open source: weights, training data, training code, and inference code. This is a big deal! Jensen said in the CES keynote yesterday that he expects open source models to catch up to proprietary models this year in a number of categories. NVIDIA is putting their weight behind making this happen. (As Alan Kay said, the best way to predict the future is to invent it.) The code for this agent is open source too, of course. You can deploy it to production with Modal and Pipecat AI cloud, or run locally on an NVIDIA DGX Spark or RTX 5090.

kwindla

274,188 views • 5 months ago

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
1:06

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

89,955 views • 1 day ago

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓
1:21

TWO BOXES THE SIZE OF A MAC MINI JUST RAN A 235 BILLION PARAMETER MODEL ON A DESK It is two NVIDIA DGX Spark units linked by a single cable. A year ago a model this size meant renting a GPU cluster by the hour. Now it sits next to your monitor for around $8,000. Here is the twist most people miss. Linking them does not create one shared 256GB memory pool. The model is split across both boxes, and that is the only reason a 235B model fits at all. It answers at roughly 10 tokens per second, and both chips sit at just 74 degrees while sipping around 50 watts. Every token stays on the desk. Nothing touches a cloud, and nothing leaves the room. The ceiling for what you can run at home just jumped from 70B to 235B. Bookmark this & Watch it run ↓

slash1s

78,502 views • 1 day ago

people burn $1,900 a month on cloud, this $2,999 NVIDIA box runs 5 AI models at once and costs $10 to power 128GB of unified memory, stack two together and you double it, enough to run models a $2,000 graphics card cannot even open in the demo it ran Qwen3 Vision, Nemotron, a voice model, text to speech and speech to text all at once, and only used half the box here is the math that makes people switch: > cloud GPUs were costing $1,900 every single month, billed forever > the box is $2,999 one time, then about $10 of electricity a month > it paid for itself in two months, $22,000 stayed in the business in year one > zero data ever leaves your desk, no rental, no rate limits most people are still renting what this owns outright the full breakdown of the box and the exact math is in the article below
1:04

people burn $1,900 a month on cloud, this $2,999 NVIDIA box runs 5 AI models at once and costs $10 to power 128GB of unified memory, stack two together and you double it, enough to run models a $2,000 graphics card cannot even open in the demo it ran Qwen3 Vision, Nemotron, a voice model, text to speech and speech to text all at once, and only used half the box here is the math that makes people switch: > cloud GPUs were costing $1,900 every single month, billed forever > the box is $2,999 one time, then about $10 of electricity a month > it paid for itself in two months, $22,000 stayed in the business in year one > zero data ever leaves your desk, no rental, no rate limits most people are still renting what this owns outright the full breakdown of the box and the exact math is in the article below

John Doe

32,178 views • 15 days ago

The bottleneck in AI has quietly shifted. - It's not the models. They are capable. - It's not the frameworks. They are mature. - It's not even the data, in many cases. When you want to train a model today, the first question isn't "what architecture should I use?" Instead, it's: "Where am I going to get infrastructure that actually works?" Not just GPUs but the entire stack: compute, deployment, scaling, storage. The traditional path is major cloud providers or specialized GPU clouds. Both have the same problem: they're built for enterprises with committed workloads, minimum spend requirements, contract negotiations, and involve quota approvals that take days. Even the "on-demand" options require you to piece together training, deployment, and scaling across different services. By the time you're actually training, hours, if not days, have passed. And there's a subtler cost: part of your brain is always managing infrastructure instead of thinking about the actual problem. I've been using Runpod for a while now, and it's the closest I've found to infrastructure that just disappears. I pay for the serverless solution by the second, and stop when I'm done. This sounds like it should be the default across all providers, but it isn't. For instance, when I'm prototyping, I don't need an H100. Instead, I need the flexibility to use cheaper GPUs that are actually available, where I can iterate fast and not worry about cost. An A40 at a few cents per hour is perfect for this. Then, when the approach is validated, I scale up. This matches how good engineering actually works. Running distributed training across multiple nodes for multi-GPU training usually requires significant infra work. RunPod abstracts most of this away. A lot of the advantage in AI comes from iteration speed. Infra that adds days of latency to that loop is a real cost, even if it's hard to measure. But good infra gets out of your way. It's available when you need it, invisible when you don't. In the video below, I have shown a simple model training workflow trained using PyTorch in Jupyter Lab. It runs in a dedicated PyTorch Pod hosted on Runpod, and I worked with the team to put this together for you. Find a link to start using Runpod in the replies!
0:23

The bottleneck in AI has quietly shifted. - It's not the models. They are capable. - It's not the frameworks. They are mature. - It's not even the data, in many cases. When you want to train a model today, the first question isn't "what architecture should I use?" Instead, it's: "Where am I going to get infrastructure that actually works?" Not just GPUs but the entire stack: compute, deployment, scaling, storage. The traditional path is major cloud providers or specialized GPU clouds. Both have the same problem: they're built for enterprises with committed workloads, minimum spend requirements, contract negotiations, and involve quota approvals that take days. Even the "on-demand" options require you to piece together training, deployment, and scaling across different services. By the time you're actually training, hours, if not days, have passed. And there's a subtler cost: part of your brain is always managing infrastructure instead of thinking about the actual problem. I've been using Runpod for a while now, and it's the closest I've found to infrastructure that just disappears. I pay for the serverless solution by the second, and stop when I'm done. This sounds like it should be the default across all providers, but it isn't. For instance, when I'm prototyping, I don't need an H100. Instead, I need the flexibility to use cheaper GPUs that are actually available, where I can iterate fast and not worry about cost. An A40 at a few cents per hour is perfect for this. Then, when the approach is validated, I scale up. This matches how good engineering actually works. Running distributed training across multiple nodes for multi-GPU training usually requires significant infra work. RunPod abstracts most of this away. A lot of the advantage in AI comes from iteration speed. Infra that adds days of latency to that loop is a real cost, even if it's hard to measure. But good infra gets out of your way. It's available when you need it, invisible when you don't. In the video below, I have shown a simple model training workflow trained using PyTorch in Jupyter Lab. It runs in a dedicated PyTorch Pod hosted on Runpod, and I worked with the team to put this together for you. Find a link to start using Runpod in the replies!

Avi Chawla

13,696 views • 5 months ago

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
0:59

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

956,471 views • 2 days ago

Ever wondered what training a former GB athlete does in his 40's as he prepares for the challenge of a lifetime? Part One:
2:18

Ever wondered what training a former GB athlete does in his 40's as he prepares for the challenge of a lifetime? Part One:

Jimmy Watkins

30,655 views • 2 years ago

🔥 NVIDIA GTC 2026: The Vera Rubin platform just dropped, introducing 10x inference throughput per watt, at 1/10th the cost per token vs. Blackwell. Jensen Huang called it: every company will now run a "token factory." Here's the thing: Aethir has been running distributed token factories since day one, with nearly 440,000+ GPU containers across 94 countries, delivering 1.5B+ compute hours to enterprises, powered by ATH. When the world's most powerful AI chips land, you need a cloud that can actually deploy them at scale, without the centralized cloud limitations and bottlenecks. That's Aethir’s advantage over centralized compute providers. ⚡
0:36

🔥 NVIDIA GTC 2026: The Vera Rubin platform just dropped, introducing 10x inference throughput per watt, at 1/10th the cost per token vs. Blackwell. Jensen Huang called it: every company will now run a "token factory." Here's the thing: Aethir has been running distributed token factories since day one, with nearly 440,000+ GPU containers across 94 countries, delivering 1.5B+ compute hours to enterprises, powered by ATH. When the world's most powerful AI chips land, you need a cloud that can actually deploy them at scale, without the centralized cloud limitations and bottlenecks. That's Aethir’s advantage over centralized compute providers. ⚡

Aethir Ecosystem

12,983 views • 2 months ago

THIS AI DEVELOPER RUNS 120B PARAMETER MODELS LOCALLY AND HIS MACBOOK PRO CAN’T EVEN OPEN THEM he bought a DGX Spark, gave it the model, went back to his desk by end of day the inference was done, tested, committed his team is still waiting for the cloud GPU queue to free up the only thing between them is 128GB of unified memory in a box smaller than your lunch one Spark is a datacenter node, two Sparks is your own cluster bookmark this and send it to whoever is still paying for cloud GPUs
2:54

THIS AI DEVELOPER RUNS 120B PARAMETER MODELS LOCALLY AND HIS MACBOOK PRO CAN’T EVEN OPEN THEM he bought a DGX Spark, gave it the model, went back to his desk by end of day the inference was done, tested, committed his team is still waiting for the cloud GPU queue to free up the only thing between them is 128GB of unified memory in a box smaller than your lunch one Spark is a datacenter node, two Sparks is your own cluster bookmark this and send it to whoever is still paying for cloud GPUs

leopardracer

83,303 views • 15 days ago

Gemma 4 31B is way too slow on my MacBook Pro M5 Max with 128GB of unified memory. 42 seconds to generate the first line of code. 21 tokens per second after that. Uses 26GB of memory when loaded. I sat there waiting nearly a minute before it even started writing code. The output? Actually decent. The lava lamp it generated looks good. But 42 seconds to first token is a dealbreaker. Claude Opus 4.7 starts generating in under 2 seconds. GPT 5.5 is instant. Good model. Unusable speed. Local inference on a $5,399 machine still can't match the cloud.
2:37

Gemma 4 31B is way too slow on my MacBook Pro M5 Max with 128GB of unified memory. 42 seconds to generate the first line of code. 21 tokens per second after that. Uses 26GB of memory when loaded. I sat there waiting nearly a minute before it even started writing code. The output? Actually decent. The lava lamp it generated looks good. But 42 seconds to first token is a dealbreaker. Claude Opus 4.7 starts generating in under 2 seconds. GPT 5.5 is instant. Good model. Unusable speed. Local inference on a $5,399 machine still can't match the cloud.

BridgeMind

39,870 views • 18 days ago

Nvidia will pay you to put a $250,000 data center outside your house you don't touch it, you don't manage it, you just collect around $1,000 a month for the electricity and Wi-Fi it uses it looks like an AC unit, it's actually 16 Blackwell GPUs running AI workloads around the clock it's built by Span, a startup Nvidia invested in to make distributed compute a reality the reason Nvidia put money into this is simple they need compute everywhere and building data centers takes years and their solution is to skip the construction entirely, use residential grid capacity and deploy through your neighborhood instead this is much cheaper, faster, and can scale to millions of homes but there is still a question nobody has answered yet, what happens if someone steals it also, technically they could give each homeowner access to a slice of the compute even 2% of 16 Blackwell GPUs is more processing power than most people will ever use bookmark this, it's worth coming back to when you have time
0:57

Nvidia will pay you to put a $250,000 data center outside your house you don't touch it, you don't manage it, you just collect around $1,000 a month for the electricity and Wi-Fi it uses it looks like an AC unit, it's actually 16 Blackwell GPUs running AI workloads around the clock it's built by Span, a startup Nvidia invested in to make distributed compute a reality the reason Nvidia put money into this is simple they need compute everywhere and building data centers takes years and their solution is to skip the construction entirely, use residential grid capacity and deploy through your neighborhood instead this is much cheaper, faster, and can scale to millions of homes but there is still a question nobody has answered yet, what happens if someone steals it also, technically they could give each homeowner access to a slice of the compute even 2% of 16 Blackwell GPUs is more processing power than most people will ever use bookmark this, it's worth coming back to when you have time

Anatoli Kopadze

402,061 views • 17 days ago

JENSEN HUANG JUST HELD UP A CHIP THAT KILLS YOUR ENTIRE AI BILL nvidia and microsoft just announced the rtx spark at computex. 1 petaflop of ai on a chip you can hold in one hand. 128gb unified memory. 20 core cpu. full nvidia stack. most people spend $200 a month on chatgpt, claude, midjourney and cursor. that is $2,400 a year renting intelligence from someone else. this chip runs all of it locally for $5 in electricity per month. developers are already offering local ai setups to small businesses for $500 a month. ten clients. $5,000 a month. one chip doing all the work. the people who move on this in 2025 will look very far ahead by 2027. save this now.
2:02

JENSEN HUANG JUST HELD UP A CHIP THAT KILLS YOUR ENTIRE AI BILL nvidia and microsoft just announced the rtx spark at computex. 1 petaflop of ai on a chip you can hold in one hand. 128gb unified memory. 20 core cpu. full nvidia stack. most people spend $200 a month on chatgpt, claude, midjourney and cursor. that is $2,400 a year renting intelligence from someone else. this chip runs all of it locally for $5 in electricity per month. developers are already offering local ai setups to small businesses for $500 a month. ten clients. $5,000 a month. one chip doing all the work. the people who move on this in 2025 will look very far ahead by 2027. save this now.

winkle.

16,535 views • 11 days ago