Loading video...

Video Failed to Load

Go Home

136 TB in 1 desktop box, and the cloud subscription for that much space costs more per year than the box itself. Most creators run 2 separate setups. A slow archive drive for finished work, and a fast NVMe drive for the project open right now. Two boxes, two...

AIMind_Ai's profile picture

AiMind

1,327 subscribers

12,351 views • 19 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

5 Comments

Cartel's profile picture
Cartel19 days ago

Damn, 136TB in one box with both fast NVMe and archive drives. Perfect for editors, no more juggling two separate setups.

0xShukshin's profile picture
0xShukshin19 days ago

worth noting: this is software RAID, and RAID 0 across those bays means zero redundancy. one drive fails, you lose the "fast" and "archive" data in the same event. one enclosure isn't the same as one backup

AiMind's profile picture
AiMind19 days ago

Fair point. You can set software RAID to 1 or 5 for redundancy, not just 0. Still keep a separate backup though.

Nexora's profile picture
Nexora18 days ago

Thanks! Now I know where I can save money.

wenWeights's profile picture
wenWeights18 days ago

Wow, 136TB in one box with fast NVMe and SATA archive. Perfect for editors, no more juggling two separate setups and cables. Cloud storage for that much space costs way more per year than the enclosure itself

Related Videos

THIS $380 BOX TURNS 166TB OF DRIVES INTO A PRIVATE CLOUD - WITHOUT A MONTHLY STORAGE PLAN. this is the ORICO HS500-Pro. 5 SATA bays 2 M.2 NVMe slots dual 2.5GbE maximum raw capacity: 166TB. CyberData OS puts project files, 4K movies, documents and photos behind one interface available from a computer, tablet or phone. the M.2 drives can handle the fast tier while five hard drives hold the archive. honest line: $380 buys the NAS, not 166TB of storage. the drives are separate, and RAID reduces usable capacity. you are not buying cloud space. you are buying the cloud. bookmark & watch today ↓
0:25

THIS $380 BOX TURNS 166TB OF DRIVES INTO A PRIVATE CLOUD - WITHOUT A MONTHLY STORAGE PLAN. this is the ORICO HS500-Pro. 5 SATA bays 2 M.2 NVMe slots dual 2.5GbE maximum raw capacity: 166TB. CyberData OS puts project files, 4K movies, documents and photos behind one interface available from a computer, tablet or phone. the M.2 drives can handle the fast tier while five hard drives hold the archive. honest line: $380 buys the NAS, not 166TB of storage. the drives are separate, and RAID reduces usable capacity. you are not buying cloud space. you are buying the cloud. bookmark & watch today ↓

Grimmer

36,071 views • 1 month ago

16 terabytes per drive, mirrored in RAID, moving over 10 gigabit - that's what kills the cloud bill. 2 terabytes of iCloud rents for about $10 a month. Google Drive charges the same for the same 2. Neither copy is yours. 1 Synology drive is 16 terabytes. 8x the space, paid once. RAID is the safety layer. Every file gets duplicated across drives, so 1 dead drive costs you a drive, not a decade of photos. That's the exact promise the cloud charges rent for. 10 gigabit LAN is the speed layer. 200GB of footage to a cloud account is an overnight job. Over 10 gigabit it's minutes. Drop 1 SSD in as the working drive and active projects open at local speed - no sync, no download, no spinner. The software is the real reason Synology over a bare box. Web apps for files and backup. iOS and Android apps that auto-pull every photo and video off the phone and the tablet, same behavior as iCloud, none of the bill. Then the media layer. Movies. A full music library served to any device - the thing Spotify and Apple Music charge $12 a month to rent you. Put a second unit in another location and one backs up the other. Off-site redundancy, 0 monthly cost. 4 subscriptions gone. 1 box. Hardware that's paid off in a year and keeps working for 8 more. Stop paying iCloud and your photos go dark. The drive just spins.
0:48

16 terabytes per drive, mirrored in RAID, moving over 10 gigabit - that's what kills the cloud bill. 2 terabytes of iCloud rents for about $10 a month. Google Drive charges the same for the same 2. Neither copy is yours. 1 Synology drive is 16 terabytes. 8x the space, paid once. RAID is the safety layer. Every file gets duplicated across drives, so 1 dead drive costs you a drive, not a decade of photos. That's the exact promise the cloud charges rent for. 10 gigabit LAN is the speed layer. 200GB of footage to a cloud account is an overnight job. Over 10 gigabit it's minutes. Drop 1 SSD in as the working drive and active projects open at local speed - no sync, no download, no spinner. The software is the real reason Synology over a bare box. Web apps for files and backup. iOS and Android apps that auto-pull every photo and video off the phone and the tablet, same behavior as iCloud, none of the bill. Then the media layer. Movies. A full music library served to any device - the thing Spotify and Apple Music charge $12 a month to rent you. Put a second unit in another location and one backs up the other. Off-site redundancy, 0 monthly cost. 4 subscriptions gone. 1 box. Hardware that's paid off in a year and keeps working for 8 more. Stop paying iCloud and your photos go dark. The drive just spins.

HodlReaper

17,435 views • 20 days ago

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.
1:00

New in Box Drive: right-click any file or folder and open it directly in the Claude or Cursor desktop apps. One right-click. One prompt. The agent reviews every contract in the folder, flags the risks, builds a comparison table and a risk memo, and saves both back to Box. All your content. Any AI agent. Right from your desktop.

Box

316,999 views • 1 month ago

UGREEN IN SHENZHEN, 2026: 4 BAYS THAT ALMOST ANYWHERE ARE DISPLAYED, AND HERE'S WHY. You've already seen the 30TB and 120TB boxes. That's a different story. Capacity isn't the issue here. Look what's inside. Four drive bays. Numbered, they slide in with a single movement. At the bottom is a memory slot. DDR5, installed in a minute. Next are two M.2 slots. You can install two NVMe SSDs, 8TB each. This isn't just storage anymore. This is hardware that you can upgrade yourself, without a service center. At the back are two LAN ports. If one link fails, the other keeps the connection. A home server with the fault tolerance of a data center. Access your files from your phone, from anywhere, without manually forwarding ports. The cloud sells you a fixed rate for years in advance. This box grows with you, add a disk, add memory, and off we go. Rent doesn't grow with you. It just gets more expensive.
0:21

UGREEN IN SHENZHEN, 2026: 4 BAYS THAT ALMOST ANYWHERE ARE DISPLAYED, AND HERE'S WHY. You've already seen the 30TB and 120TB boxes. That's a different story. Capacity isn't the issue here. Look what's inside. Four drive bays. Numbered, they slide in with a single movement. At the bottom is a memory slot. DDR5, installed in a minute. Next are two M.2 slots. You can install two NVMe SSDs, 8TB each. This isn't just storage anymore. This is hardware that you can upgrade yourself, without a service center. At the back are two LAN ports. If one link fails, the other keeps the connection. A home server with the fault tolerance of a data center. Access your files from your phone, from anywhere, without manually forwarding ports. The cloud sells you a fixed rate for years in advance. This box grows with you, add a disk, add memory, and off we go. Rent doesn't grow with you. It just gets more expensive.

Kirill

580,975 views • 13 days ago

APPLE SOLD THIS 39.9-POUND TOWER FOR $2,499 IN 2009 - ONE LATCH TURNED THE ENTIRE MACHINE INTO A WORKBENCH. this is the Early 2009 Mac Pro. the video shows the part spec sheets rarely capture. pull one latch and the aluminum side panel comes away. the memory, graphics card, drive bays and expansion slots are immediately visible. no hidden screws before you can inspect the machine. no loose SATA cables hanging from every drive. the base model shipped with: 2.66GHz quad-core Xeon 3GB of 1066MHz DDR3 ECC memory 640GB SATA hard drive GeForce GT 120 with 512MB of memory four PCIe 2.0 slots. the quad-core model supported up to 16GB of RAM. storage was handled by four cable-free carriers that connected directly inside the chassis. the case also left space for two optical drives. the rear panel carried hardware that now feels like an archive: dual Gigabit Ethernet optical audio USB 2.0 FireWire 800. the GT 120 offered Mini DisplayPort and dual-link DVI. install four of those cards and Apple rated the tower for up to eight 30-inch displays. the enclosure measured 20.1 inches tall and weighed almost 40 pounds before serious upgrades. this was not a compact desktop. it was a machine designed to be opened, understood and rebuilt. honest line: the Xeon, GT 120, SATA drive and USB 2.0 ports are ancient by modern standards. beautiful serviceability does not make old hardware fast. those parts aged. the enclosure did not. 17 years later, the most impressive component is still the case. bookmark & watch today ↓
0:53

APPLE SOLD THIS 39.9-POUND TOWER FOR $2,499 IN 2009 - ONE LATCH TURNED THE ENTIRE MACHINE INTO A WORKBENCH. this is the Early 2009 Mac Pro. the video shows the part spec sheets rarely capture. pull one latch and the aluminum side panel comes away. the memory, graphics card, drive bays and expansion slots are immediately visible. no hidden screws before you can inspect the machine. no loose SATA cables hanging from every drive. the base model shipped with: 2.66GHz quad-core Xeon 3GB of 1066MHz DDR3 ECC memory 640GB SATA hard drive GeForce GT 120 with 512MB of memory four PCIe 2.0 slots. the quad-core model supported up to 16GB of RAM. storage was handled by four cable-free carriers that connected directly inside the chassis. the case also left space for two optical drives. the rear panel carried hardware that now feels like an archive: dual Gigabit Ethernet optical audio USB 2.0 FireWire 800. the GT 120 offered Mini DisplayPort and dual-link DVI. install four of those cards and Apple rated the tower for up to eight 30-inch displays. the enclosure measured 20.1 inches tall and weighed almost 40 pounds before serious upgrades. this was not a compact desktop. it was a machine designed to be opened, understood and rebuilt. honest line: the Xeon, GT 120, SATA drive and USB 2.0 ports are ancient by modern standards. beautiful serviceability does not make old hardware fast. those parts aged. the enclosure did not. 17 years later, the most impressive component is still the case. bookmark & watch today ↓

Grimmer

224,481 views • 28 days ago

One more time for the people in the back…. YOU CAN’T LEARN TO DRIVE IN PARKED CAR! MOVE and take ACTION! 💯 COMMENT “#MAXOUT”
0:51

One more time for the people in the back…. YOU CAN’T LEARN TO DRIVE IN PARKED CAR! MOVE and take ACTION! 💯 COMMENT “#MAXOUT”

Ed Mylett

11,016 views • 3 years ago

THIS 316TB PRIVATE CLOUD FITS UNDER A DESK - 12 DRIVES, DUAL 10GBE AND NO MONTHLY STORAGE PLAN. this ORICO CF1000 build combines: 10 x 30TB hard drives 2 x 8TB NVMe SSDs raw total: 316TB. the ten SATA bays handle the bulk storage, while two internal M.2 slots add fast solid-state capacity. inside is a 12-core Intel Core i5-1240P with 32GB DDR5, expandable to 96GB. two 10GbE ports can aggregate up to 20GbE. RAID 0, 1, 5, 6, 10, 50 and 60 are supported. honest line: 316TB is raw capacity. formatting and RAID reduce the usable space. ORICO's current official spec lists a 256TB maximum with 24TB per SATA bay, so the 30TB drives shown here sit beyond its published support matrix. the cloud did not disappear. it just moved under the desk. bookmark & watch today ↓
0:24

THIS 316TB PRIVATE CLOUD FITS UNDER A DESK - 12 DRIVES, DUAL 10GBE AND NO MONTHLY STORAGE PLAN. this ORICO CF1000 build combines: 10 x 30TB hard drives 2 x 8TB NVMe SSDs raw total: 316TB. the ten SATA bays handle the bulk storage, while two internal M.2 slots add fast solid-state capacity. inside is a 12-core Intel Core i5-1240P with 32GB DDR5, expandable to 96GB. two 10GbE ports can aggregate up to 20GbE. RAID 0, 1, 5, 6, 10, 50 and 60 are supported. honest line: 316TB is raw capacity. formatting and RAID reduce the usable space. ORICO's current official spec lists a 256TB maximum with 24TB per SATA bay, so the 30TB drives shown here sit beyond its published support matrix. the cloud did not disappear. it just moved under the desk. bookmark & watch today ↓

Grimmer

16,226 views • 1 month ago

Daniel Kahneman, Nobel laureate and author of "Thinking, Fast and Slow": "You have two minds. one is fast, confident and usually wrong about money. the other is slow, lazy, and the only one that can do the math. I won a Nobel showing the casino lives off the first one, because it shows up before the second one wakes up." this free lecture holds the entire "trust your instincts" the gurus sell, from the Nobel laureate who proved your instincts are the trap. at the board it's simple. Kahneman split the mind in two. System 1 is fast, automatic and sure of itself. System 2 is slow, effortful, and the only part that actually computes the odds. the catch is that System 1 answers first and System 2 is lazy, so you act on a feeling and build the reasons afterward. the casino and the market are timed to catch you in that first second. that's the whole "instinct edge", minus the marketing. Kahneman worked this out over fifty years and put it in one book in 2011. it has been public ever since. same point as my casino piece above: the house wins because your fast mind calls luck skill before your slow mind can check the math. the science is free and half the world has read the book. what nobody can sell you is the discipline to wake the slow mind up before you click buy. that one pause is the whole edge, and no lecture can force you to take it.
1:12:52

Daniel Kahneman, Nobel laureate and author of "Thinking, Fast and Slow": "You have two minds. one is fast, confident and usually wrong about money. the other is slow, lazy, and the only one that can do the math. I won a Nobel showing the casino lives off the first one, because it shows up before the second one wakes up." this free lecture holds the entire "trust your instincts" the gurus sell, from the Nobel laureate who proved your instincts are the trap. at the board it's simple. Kahneman split the mind in two. System 1 is fast, automatic and sure of itself. System 2 is slow, effortful, and the only part that actually computes the odds. the catch is that System 1 answers first and System 2 is lazy, so you act on a feeling and build the reasons afterward. the casino and the market are timed to catch you in that first second. that's the whole "instinct edge", minus the marketing. Kahneman worked this out over fifty years and put it in one book in 2011. it has been public ever since. same point as my casino piece above: the house wins because your fast mind calls luck skill before your slow mind can check the math. the science is free and half the world has read the book. what nobody can sell you is the discipline to wake the slow mind up before you click buy. that one pause is the whole edge, and no lecture can force you to take it.

Rossst.03

197,883 views • 1 month ago

Here are two different explanations for tides. One from the globe model and one modeled on a level plane. Watch both and you decide which one makes more sense.
2:05

Here are two different explanations for tides. One from the globe model and one modeled on a level plane. Watch both and you decide which one makes more sense.

Ted Logan

16,876 views • 5 months ago

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.
1:16

This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B at home, after dropping his $1,999-a-month cloud bill to zero. He wired 2 small boxes into a single computer, split a giant 235-billion-parameter model in half between them, and serves it across his own network at about 10 tokens a second, with no internet, no cloud, right there on the desk. No data center, no thousand-dollar graphics cards, no monthly cloud bill. Just him, 2 gold boxes the size of a sandwich, one cable between them, and 1 power strip. And here is the whole payoff. He used to pay the cloud $1,999 a month for the same model, and the meter ticked on every request. Now he paid $5,998 once for 2 boxes, they covered their cost in 3 months, and after that he sends as many requests as he wants for free, only electricity. The two Sparks talk over one fast cable, each holds 128GB of memory, and together they carry the whole model, about 73GB loaded per box, with the chip inside pinned near the limit at 96%. Both boxes work as one and keep trading data over the cable, with no cloud in the loop and no single word leaking out. The ready model sits on one local address, and any app on his network calls it as easily as ChatGPT. And here is how he described, in plain words, what this pair of boxes does: "this is a pair of boxes that holds the huge Qwen3-235B model and serves it to one network. the model is split in half, and each box owns its half. parts: // Box 1 (holds the first half of the model and starts the answer fast, the first word appears in under a second) // Box 2 (holds the second half and writes out the rest, about 10 tokens a second) // Cable (connects the 2 boxes and moves data between them on every step, with no lag) // Address (one local address where any app sends its request, like to a cloud model) // Test (a script that runs big prompts through and measures speed and delays) // Monitor (checks temperature, power draw, and load on both boxes every 2 seconds). the model never goes to the cloud. he only steps in when a box runs hotter than 80 degrees or the cable between them starts dropping data." So the system knows exactly what it is, what it is for, and where its limits are. It knows it has to hold the whole huge model across 2 boxes on its own. It knows it has to answer every request locally, with no meter, no limits, and no internet. It knows the human is only needed when a box overheats or the link between them stalls. → The setup runs around the clock on 2 boxes, each pulling under 60 watts → However many requests he sends, the monthly bill is $0, only electricity → The first box starts the answer in under a second → The second writes text at about 10 tokens a second → One request at a time: 838 tokens in 85 seconds, first word in 0.8s → Two requests at once: 697 tokens in 108 seconds, first word in 0.7s → Both boxes sit at 96% load and warm up to 76-78 degrees And only when a chip in a box runs hotter than 80 degrees or the cable between the 2 Sparks drops data does the system call the owner. And when he himself is out on a run or in a coffee shop, he still reaches his own model at home from his phone: sends a big prompt to the local Qwen3-235B, gets the full answer back in under a minute and a half, with no token meter ticking and no limit to hit. Here is what the test shows on his screen during one of the night runs: "one request at a time: 838 tokens in 84.9 seconds, first word in 0.8s, then 0.1s per token." "two requests at once: 697 tokens in 107.6 seconds, first word in 0.7s, then 0.15s per token." "Box 1: chip at 96% load, 76 degrees, 56 watts, 73GB used in memory." "Box 2: chip at 96% load, 78 degrees, 56 watts, the Qwen3-235B model fully loaded." And while everyone around is paying for AI by the month and bumping into limits, his top-tier model just sits on the desk and works as much as he wants: his own little power plant instead of a forever meter. He has no server rack of his own and no cloud account behind it. Just 2 DGX Spark boxes on a desk, one model split in half between them, one local address, and a folder of prompts next to it. Out of everything I have seen this year, this is the cleanest way to stop paying for AI: $5,998 of hardware on the desk once, $0 a month to the cloud, unlimited forever, and between them 2 gold boxes, 1 cable, and the full Qwen3-235B answering at home with no internet.

Blaze

93,871 views • 3 months ago

Draymond Green says players should be required to stay in college for 2 years before entering the NBA “I don’t think there should be one-and-done. I think what you’re teaching kids with the one-and-done rule is to go to a place for five months, be one foot in, one foot out, and then go on your way” “You’re in college for two years, and you’re committed to something for two years. A team commits to you for two years. If you’re a first round pick, you get two guaranteed years, and then there’s team options. I think it aligns with the two year thing” “You’re making a two year commitment. They’re making a two year commitment to you. It familiarizes the college student with NBA rules right away when you talk about a two year commitment. What you can do, what you need to do over the course of two years” “I would change that. The one-and-done thing has never quite been right. You get people on a campus for five or six months, they’re one foot in, they’re one foot out. I just don’t think it’s a recipe for success”
1:06

Draymond Green says players should be required to stay in college for 2 years before entering the NBA “I don’t think there should be one-and-done. I think what you’re teaching kids with the one-and-done rule is to go to a place for five months, be one foot in, one foot out, and then go on your way” “You’re in college for two years, and you’re committed to something for two years. A team commits to you for two years. If you’re a first round pick, you get two guaranteed years, and then there’s team options. I think it aligns with the two year thing” “You’re making a two year commitment. They’re making a two year commitment to you. It familiarizes the college student with NBA rules right away when you talk about a two year commitment. What you can do, what you need to do over the course of two years” “I would change that. The one-and-done thing has never quite been right. You get people on a campus for five or six months, they’re one foot in, they’re one foot out. I just don’t think it’s a recipe for success”

dank

37,741 views • 21 days ago

Pope Leo challenges students participating in the Jubilee of the World of Education to work for a better society through education, which is “one of the most beautiful and powerful tools for changing the world.” “How wonderful it would be if one day your generation were remembered as the ‘generation plus,’ remembered for the extra drive you brought to the Church and the world,” Pope Leo said. But he also warned against keeping this desire a dream. The Pope explained the answer to achieving this is through education, “one of the most beautiful and powerful tools for changing the world.”
0:42

Pope Leo challenges students participating in the Jubilee of the World of Education to work for a better society through education, which is “one of the most beautiful and powerful tools for changing the world.” “How wonderful it would be if one day your generation were remembered as the ‘generation plus,’ remembered for the extra drive you brought to the Church and the world,” Pope Leo said. But he also warned against keeping this desire a dream. The Pope explained the answer to achieving this is through education, “one of the most beautiful and powerful tools for changing the world.”

Vatican News

20,124 views • 10 months 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

48,135 views • 3 months ago

2,934 MB/s write lands on the RAID 0 volume before the second drive even finishes mounting. Two Samsung 990 PROs sit in the top bays of the silver chassis. The cover screws down. One cable carries everything. Blackmagic fills every ProRes and H.265 checkbox green at 2,881 MB/s read. A 27 GB project folder finishes in 9 seconds. The aluminum box stays under 40 °C while three monitors run simultaneous timelines and the entire library stays local.
0:38

2,934 MB/s write lands on the RAID 0 volume before the second drive even finishes mounting. Two Samsung 990 PROs sit in the top bays of the silver chassis. The cover screws down. One cable carries everything. Blackmagic fills every ProRes and H.265 checkbox green at 2,881 MB/s read. A 27 GB project folder finishes in 9 seconds. The aluminum box stays under 40 °C while three monitors run simultaneous timelines and the entire library stays local.

HodlReaper

14,854 views • 24 days ago

Hyundai makes its grand debut on Asphalt Legends Unite with two cutting-edge models. Storm the streets with two revolutionary rides – the IONIQ 5 N and the N Vision 74. ​ Both cars are featured in a time-limited event starting today. Boot up and be one of the first legends to drive them in-game. Register in the web form and race for a chance to win a trip to South Korea for an exclusive Hyundai experience:
1:00

Hyundai makes its grand debut on Asphalt Legends Unite with two cutting-edge models. Storm the streets with two revolutionary rides – the IONIQ 5 N and the N Vision 74. ​ Both cars are featured in a time-limited event starting today. Boot up and be one of the first legends to drive them in-game. Register in the web form and race for a chance to win a trip to South Korea for an exclusive Hyundai experience:

Asphalt

17,498 views • 1 year ago

Richard Childress indicates that Austin Hill will drive the No. 33 Chevrolet, in place of the late Kyle Busch, for the rest of the season. "For right now, Austin is gonna drive - as far as we're concerned - the rest of the year. We don't want to put a burden back on everybody trying to go from one driver to the other one."
0:52

Richard Childress indicates that Austin Hill will drive the No. 33 Chevrolet, in place of the late Kyle Busch, for the rest of the season. "For right now, Austin is gonna drive - as far as we're concerned - the rest of the year. We don't want to put a burden back on everybody trying to go from one driver to the other one."

Steven Taranto

31,294 views • 3 months ago

Hypnotizing Hips AND Booty Shake for Silly Jester! For folks that got both, you can choose between two separate loops or one larger loop like this :3 Check out the full res animations in my MEGA archive:
0:30

Hypnotizing Hips AND Booty Shake for Silly Jester! For folks that got both, you can choose between two separate loops or one larger loop like this :3 Check out the full res animations in my MEGA archive:

fucker bun (COMMS AND YCH OPEN)

11,657 views • 9 months ago

THIS GUY PUT FABLE, GPT 5.6 SOL, AND OPUS IN ONE SHARED CHAT AND HAS THEM TAG EACH OTHER LIKE COWORKERS instead of running three separate models in three separate windows and copy pasting between them, they all sit in one room and talk to each other > you tag whichever model you want and only that one responds > they tag each other too, so fable can hand something to opus, opus can pull in sol for a second opinion > each agent only sees the messages theyre mentioned in, but you get to read everything > he had them running and orchestrating together for more than a day straight the best part is how different each one actually behaves: > fable is the creative product manager. huge context window so it remembers everything, and its the one finding the out of the box solutions > sol is the obsessive tech lead. it will trace every bug to the exact source and stress test every edge case before writing a single line > opus is the workhorse engineer. smart enough for almost anything, and it constantly questions things, which forces the other two to re-examine their own solutions its like managing a team. one plans, one writes the code, one reviews it, and they hand work back and forth without you playing middleman everyone else is arguing about which model is best right now, but the real play is making them work together at the same time
1:11

THIS GUY PUT FABLE, GPT 5.6 SOL, AND OPUS IN ONE SHARED CHAT AND HAS THEM TAG EACH OTHER LIKE COWORKERS instead of running three separate models in three separate windows and copy pasting between them, they all sit in one room and talk to each other > you tag whichever model you want and only that one responds > they tag each other too, so fable can hand something to opus, opus can pull in sol for a second opinion > each agent only sees the messages theyre mentioned in, but you get to read everything > he had them running and orchestrating together for more than a day straight the best part is how different each one actually behaves: > fable is the creative product manager. huge context window so it remembers everything, and its the one finding the out of the box solutions > sol is the obsessive tech lead. it will trace every bug to the exact source and stress test every edge case before writing a single line > opus is the workhorse engineer. smart enough for almost anything, and it constantly questions things, which forces the other two to re-examine their own solutions its like managing a team. one plans, one writes the code, one reviews it, and they hand work back and forth without you playing middleman everyone else is arguing about which model is best right now, but the real play is making them work together at the same time

Om Patel

22,998 views • 1 month ago

NVIDIA quietly built two desktop boxes that delete a $25,000/year AI subscription bill You don't rewrite your stack, you don't rent another data center, you just plug both into the wall and switch one line of code One looks like a deck of cards, the other like a hardback novel, together they replace ChatGPT Plus, Claude Pro, Cursor Pro, the OpenAI API meter, and every cloud GPU you were renting for fine-tunes It's built on the same CUDA stack the data center runs, which means once you migrate one workflow the rest follow on the same code path The reason NVIDIA shipped this is simple The bigger you scale on cloud AI, the harder you get taxed, and a one-person operator paying $2,100/month is producing exactly $0 of asset value at the end of every month And their solution is to skip the rental meter entirely, push inference back onto your desk, and let you loop agents overnight without watching a number tick on someone else's invoice This is much cheaper, faster, and pays itself back in 6 weeks for anyone already running AI for work But there is still a question nobody has answered yet, what happens when the next frontier model drops and your local 70B falls 6 months behind mid-quarter Also, technically a stack of four of the big box runs a 1.6 trillion parameter model on a desk for under $12,000 Even a fraction of that compute is more than most people will ever need in a year Bookmark this, it's worth coming back to when you have time 👇
0:35

NVIDIA quietly built two desktop boxes that delete a $25,000/year AI subscription bill You don't rewrite your stack, you don't rent another data center, you just plug both into the wall and switch one line of code One looks like a deck of cards, the other like a hardback novel, together they replace ChatGPT Plus, Claude Pro, Cursor Pro, the OpenAI API meter, and every cloud GPU you were renting for fine-tunes It's built on the same CUDA stack the data center runs, which means once you migrate one workflow the rest follow on the same code path The reason NVIDIA shipped this is simple The bigger you scale on cloud AI, the harder you get taxed, and a one-person operator paying $2,100/month is producing exactly $0 of asset value at the end of every month And their solution is to skip the rental meter entirely, push inference back onto your desk, and let you loop agents overnight without watching a number tick on someone else's invoice This is much cheaper, faster, and pays itself back in 6 weeks for anyone already running AI for work But there is still a question nobody has answered yet, what happens when the next frontier model drops and your local 70B falls 6 months behind mid-quarter Also, technically a stack of four of the big box runs a 1.6 trillion parameter model on a desk for under $12,000 Even a fraction of that compute is more than most people will ever need in a year Bookmark this, it's worth coming back to when you have time 👇

ZEUS⚡️

108,199 views • 3 months ago

NVIDIA WILL PAY YOU $150/MONTH TO BOLT 16 BLACKWELL GPUS TO YOUR HOUSE - OR YOU BUY THE BOX AND MAKE $22,000 A YEAR same NVIDIA chips. the contract is where it gets interesting. they attach a $1,000,000 data center to your house and pay you for it - you get free internet, battery backup and cheaper electricity while they run an asset serving Amazon, Microsoft and Google 24/7 on your property or you spend $2,999 on a DGX Spark the size of a paperback - 128GB memory, runs a 70B model locally, $10/month in electricity if you were paying $1,900/month on cloud GPU rentals it pays for itself in 6 weeks and puts $22,000 back in year one one contract you are the infrastructure. the other one you own it.
0:30

NVIDIA WILL PAY YOU $150/MONTH TO BOLT 16 BLACKWELL GPUS TO YOUR HOUSE - OR YOU BUY THE BOX AND MAKE $22,000 A YEAR same NVIDIA chips. the contract is where it gets interesting. they attach a $1,000,000 data center to your house and pay you for it - you get free internet, battery backup and cheaper electricity while they run an asset serving Amazon, Microsoft and Google 24/7 on your property or you spend $2,999 on a DGX Spark the size of a paperback - 128GB memory, runs a 70B model locally, $10/month in electricity if you were paying $1,900/month on cloud GPU rentals it pays for itself in 6 weeks and puts $22,000 back in year one one contract you are the infrastructure. the other one you own it.

Sprytix

26,247 views • 3 months ago