Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

NVIDIA SOLD THESE TESLA K80s FOR $5,000 EACH AND KILLED DRIVER SUPPORT FOR THEM IN 2018. HE PAID $578 FOR THE WHOLE 24-CORE WORKSTATION AND 48GB OF VRAM CAME WITH IT 00:12 he wipes three years of dust off the case and says "back in april of 2023 I...

antisadh's profile picture

Antid

2,482 subscribers

49,589 Aufrufe • vor 10 Tagen •via X (Twitter)

Wissenschaft & TechnologieFinanzen
LIVE

Anya Rossi• Live Now

Private livecam show

14 Kommentare

Profilbild von Ahmad Waqass Goraya Baloch 🇵🇸
Ahmad Waqass Goraya Baloch 🇵🇸vor 10 Tagen

Usual social media grabage. Ddr3 ram system with ancient CPU and slower tesla is waste of money. It uses energy like a power house. Whole system slower than a good ryzen system.

Profilbild von BLB_Genome
BLB_Genomevor 9 Tagen

SLA doesn't double VRAM. It just shares the load between the two. You will only utilize 24GB, technically.

Profilbild von John D. Pope 🦒
John D. Pope 🦒vor 10 Tagen

Missing the scoop on intel optane memory

Profilbild von rewind
rewindvor 10 Tagen

that fan shroud is commitment

Profilbild von 𝚜𝚘𝚏𝚝𝚏𝚕𝚘𝚠𝟿𝚟𝚓𝚌
𝚜𝚘𝚏𝚝𝚏𝚕𝚘𝚠𝟿𝚟𝚓𝚌vor 10 Tagen

@grok real or cap?

Profilbild von machi nothing can stop this 47
machi nothing can stop this 47vor 10 Tagen

Yep k80s not worth, almost the right choice my friend

Profilbild von ZeroCaresGiven
ZeroCaresGivenvor 8 Tagen

Geez bro finger long af

Profilbild von Stewart-Ever Queer
Stewart-Ever Queervor 8 Tagen

a 2690 v3? 😂😂😂😂😂😂😂😂😂 I had some of those. SO BAD. 2680 v4 and i put 1tb ram and a ton of p100 and a2000s

Profilbild von R Burke
R Burkevor 9 Tagen

I have one of these z840s. Only one xeon cpu loaded in the dual config. 256gb registered DDR4. ~16tb HDD. Sata SSD boot. Quadro M4000. I pulled the RAM and listed them on ebay. Everything else is meh. Maybe I'll pull the drives and GPU and list the Z840.

Profilbild von Steve
Stevevor 10 Tagen

Never do this. ever. Especially today.

Profilbild von Avid
Avidvor 10 Tagen

nice post

Profilbild von BonBonaz
BonBonazvor 10 Tagen

that's wild, but is it really worth digging out old tech like that?

Profilbild von JustX
JustXvor 5 Tagen

Followed, fun video!

Profilbild von Daniel rivera
Daniel riveravor 5 Tagen

@grok why build this

Ähnliche Videos

NVIDIA KILLED DRIVER SUPPORT FOR THESE IN 2018. HE BOUGHT TWO OFF EBAY FOR $150 ANYWAY AND SPENT A WEEKEND WATCHING THEM REFUSE TO POST. KIMI DOES THE SAME WORK FOR $19/MO 03:11 he's holding a molex adapter he already knows is a mistake and says "this is so not a good idea, like this is a pretty foolish idea, I should not be doing this really" 2 tesla k80s for $150 -> 48gb of vram on paper -> no video out on either card -> no video out on the motherboard either -> hunt down a single-slot gpu just to see BIOS -> the y-splitter that shipped with them is bridged wrong -> improvise from three 6-pin rails -> 266 watts at idle -> 6 beeps -> nothing on screen kepler shipped in 2014, nvidia cut cuda support in 2018, and datacenters dumped millions of these onto ebay where they still list as "AI accelerator, 24GB" because 24 is a bigger number than 12 and nobody checks the compute capability the honest part: he swapped both cards, pulled the sata power, ran one alone off the correct rails, and neither one posted, the host boots fine with the slot empty, $150 gone and the weekend with it 2x tesla k80 + dual xeon host + 3d printed 120mm shroud + molex-to-8pin adapters + 6 bios beeps + zero tokens generated watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below
6:17

NVIDIA KILLED DRIVER SUPPORT FOR THESE IN 2018. HE BOUGHT TWO OFF EBAY FOR $150 ANYWAY AND SPENT A WEEKEND WATCHING THEM REFUSE TO POST. KIMI DOES THE SAME WORK FOR $19/MO 03:11 he's holding a molex adapter he already knows is a mistake and says "this is so not a good idea, like this is a pretty foolish idea, I should not be doing this really" 2 tesla k80s for $150 -> 48gb of vram on paper -> no video out on either card -> no video out on the motherboard either -> hunt down a single-slot gpu just to see BIOS -> the y-splitter that shipped with them is bridged wrong -> improvise from three 6-pin rails -> 266 watts at idle -> 6 beeps -> nothing on screen kepler shipped in 2014, nvidia cut cuda support in 2018, and datacenters dumped millions of these onto ebay where they still list as "AI accelerator, 24GB" because 24 is a bigger number than 12 and nobody checks the compute capability the honest part: he swapped both cards, pulled the sata power, ran one alone off the correct rails, and neither one posted, the host boots fine with the slot empty, $150 gone and the weekend with it 2x tesla k80 + dual xeon host + 3d printed 120mm shroud + molex-to-8pin adapters + 6 bios beeps + zero tokens generated watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below

Antid

54,180 Aufrufe • vor 18 Tagen

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year
1:16

INTEL JUST SHIPPED A WORKSTATION CARD WITH TWO GPUs ON ONE PCB AND 48GB OF VRAM. FOUR CARDS GIVE A SINGLE MOTHERBOARD 192GB OF POOLED INFERENCE MEMORY FOR THE PRICE OF TWO RTX 5090s 00:14 he holds one card up to the camera, two GPU dies side by side under the cooler, each one running its own x8 PCIe lane back to the chipset the cluster sees eight discrete accelerators in software. intel's Battle Matrix stack shards a model across all eight, so a 235B parameter network loads in slices and answers requests in parallel what 192GB of VRAM unlocks: an entire 200B class model in memory without quantization. a vision agent reading 100 invoices at once. a research box that holds three frontier models loaded simultaneously, switching between them in under a second intel is the slow side of inference. nvidia is faster per token, that is the honest tradeoff. but the only other path to this much VRAM is a $40,000 nvidia rack or three networked Mac Studios four B60 cards plus the chassis lands under $5,000. power draw averages 800 watts, $55 a month in electricity. one engineer paying $400 a month for combined ChatGPT Pro and Claude Code Max pays the hardware off in less than a year

NO1ennn

48,247 Aufrufe • vor 2 Monaten

7-YEAR-OLD RASPBERRY PI WITH 2GB OF RAM IS RUNNING DEEPSEEK RIGHT NOW WHILE SAM ALTMAN BILLS $200/MO AND DARIO AMODEI BILLS $200/MO FOR A MODEL YOU NEVER GET TO KEEP 00:34 he points at the smallest board on the bench and says "out of all these I'm genuinely shocked that I actually got it up and running on this raspberry pi 4b with 2 gigs of ram" raspberry pi 4b, 2gb, seven years old -> ollama with deepseek r1 1.5b -> a dell micro form factor doing cpu-only inference next to it -> an m1 max macbook with 64gb unified memory beating the dual gpu tower on large models -> four machines, four architectures, all serving locally apple's unified memory puts the ram on the same die as the cpu and gpu, so a laptop outruns a two-card workstation on big models, and the cheapest board on that bench costs less than four days of a claude max seat the honest part: 2gb is the actual floor and he says it was rough to get there, a 4gb or 8gb pi would have taken minutes instead, and 1.5b parameters is a model you use for structure not for answers raspberry pi 4b 2gb + dell micro form factor + m1 max 64gb + dual gpu tower + ollama + deepseek r1 watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below
3:16

7-YEAR-OLD RASPBERRY PI WITH 2GB OF RAM IS RUNNING DEEPSEEK RIGHT NOW WHILE SAM ALTMAN BILLS $200/MO AND DARIO AMODEI BILLS $200/MO FOR A MODEL YOU NEVER GET TO KEEP 00:34 he points at the smallest board on the bench and says "out of all these I'm genuinely shocked that I actually got it up and running on this raspberry pi 4b with 2 gigs of ram" raspberry pi 4b, 2gb, seven years old -> ollama with deepseek r1 1.5b -> a dell micro form factor doing cpu-only inference next to it -> an m1 max macbook with 64gb unified memory beating the dual gpu tower on large models -> four machines, four architectures, all serving locally apple's unified memory puts the ram on the same die as the cpu and gpu, so a laptop outruns a two-card workstation on big models, and the cheapest board on that bench costs less than four days of a claude max seat the honest part: 2gb is the actual floor and he says it was rough to get there, a 4gb or 8gb pi would have taken minutes instead, and 1.5b parameters is a model you use for structure not for answers raspberry pi 4b 2gb + dell micro form factor + m1 max 64gb + dual gpu tower + ollama + deepseek r1 watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below

Antid

10,442 Aufrufe • vor 11 Tagen

NVIDIA WANTS $2,000 FOR 16GB OF VRAM. SONY'S PS5 CHIP DOES IT FOR $80 AND BITCOIN OPERATIONS ARE LIQUIDATING THEM FASTER THAN EBAY CAN LIST THEM, THE PRICE JUMPED 50% IN THREE WEEKS 01:01 he holds it up to the camera and says "these were originally produced for mining bitcoin, but now a lot of bitcoin operations are starting to sell these off" $80 bc250 off ebay -> a slimmed down ps5 apu with 16gb of shared gddr6 -> m.2 slot, sata, dual ethernet, displayport, all on the card -> $50 flex itx psu -> 3d print the case, then 3d print a second tool just to pry the heatsink fins open -> clip a fan onto it -> ubuntu and ollama in one curl line nvidia charges $2,000 for a card with this much vram and sony put the same class of silicon in 117 million consoles, then bitcoin operators bought the mining variant by the pallet and started dumping it, the listings went from $80 to $120 in three weeks and they are still moving the honest part: these shipped as rack cards with server fans screaming through a row of them, pull one out alone and it has no cooling story at all, the entire diy scene exists because this hardware was never meant to live outside a rack amd bc250 + 16gb shared gddr6 + flex itx psu + 3d printed case and fin tool + ubuntu + ollama watch and save it, elon open sourced grok's body and moonshot open sourced kimi's brain, the full $600 to $14 build is in the article below
2:18

NVIDIA WANTS $2,000 FOR 16GB OF VRAM. SONY'S PS5 CHIP DOES IT FOR $80 AND BITCOIN OPERATIONS ARE LIQUIDATING THEM FASTER THAN EBAY CAN LIST THEM, THE PRICE JUMPED 50% IN THREE WEEKS 01:01 he holds it up to the camera and says "these were originally produced for mining bitcoin, but now a lot of bitcoin operations are starting to sell these off" $80 bc250 off ebay -> a slimmed down ps5 apu with 16gb of shared gddr6 -> m.2 slot, sata, dual ethernet, displayport, all on the card -> $50 flex itx psu -> 3d print the case, then 3d print a second tool just to pry the heatsink fins open -> clip a fan onto it -> ubuntu and ollama in one curl line nvidia charges $2,000 for a card with this much vram and sony put the same class of silicon in 117 million consoles, then bitcoin operators bought the mining variant by the pallet and started dumping it, the listings went from $80 to $120 in three weeks and they are still moving the honest part: these shipped as rack cards with server fans screaming through a row of them, pull one out alone and it has no cooling story at all, the entire diy scene exists because this hardware was never meant to live outside a rack amd bc250 + 16gb shared gddr6 + flex itx psu + 3d printed case and fin tool + ubuntu + ollama watch and save it, elon open sourced grok's body and moonshot open sourced kimi's brain, the full $600 to $14 build is in the article below

Antid

59,393 Aufrufe • vor 14 Tagen

48GB of VRAM rents for $500 a month, and this rig has room to double it. A vertical frame. A bare motherboard. One graphics card, exposed and humming. No rack. No server room. Just a desk. Ryzen 9 9950x. AsRock Taichi X870E. 96GB of DDR5 at 6000MT/s. A Thermalright Royal Pretor 130 Ultra on top. A 1300-watt Super Flower supply feeding all of it. One card. 48GB of VRAM. On the open market, that card alone rents for $0.58 to $0.82 an hour. Run it around the clock, and it clears $500 a month, crunching someone else's AI workloads. The motherboard and the power supply were not picked at random. Both, for one reason: a second GPU. Slide it in, and VRAM doubles to 96GB. So does the money: $1,000 a month, from a machine that fits under a desk. Most people rent that power by the hour. This desk prints it.
0:54

48GB of VRAM rents for $500 a month, and this rig has room to double it. A vertical frame. A bare motherboard. One graphics card, exposed and humming. No rack. No server room. Just a desk. Ryzen 9 9950x. AsRock Taichi X870E. 96GB of DDR5 at 6000MT/s. A Thermalright Royal Pretor 130 Ultra on top. A 1300-watt Super Flower supply feeding all of it. One card. 48GB of VRAM. On the open market, that card alone rents for $0.58 to $0.82 an hour. Run it around the clock, and it clears $500 a month, crunching someone else's AI workloads. The motherboard and the power supply were not picked at random. Both, for one reason: a second GPU. Slide it in, and VRAM doubles to 96GB. So does the money: $1,000 a month, from a machine that fits under a desk. Most people rent that power by the hour. This desk prints it.

AiMind

30,720 Aufrufe • vor 22 Tagen

Someone put 1TB of RAM and 48GB of VRAM into a workstation just to run AI. This is an HP Z8 G4 with two 24-core Xeons, 96 threads, 1TB of RAM and an NVIDIA RTX A6000. On paper, it looks excessive. But for local AI, there’s a reason this kind of hardware still makes sense. The A6000 has 48GB of VRAM, while the system has another 1TB of RAM behind it. That gives you a lot more room for large models without immediately running into memory limits. The interesting part is that none of this is cutting-edge hardware. It’s an older workstation being reused for a workload that didn’t exist at this scale when the machine was designed. And that’s becoming one of the best things about Local AI: you don't always need new hardware. Sometimes you just need enough memory.
0:47

Someone put 1TB of RAM and 48GB of VRAM into a workstation just to run AI. This is an HP Z8 G4 with two 24-core Xeons, 96 threads, 1TB of RAM and an NVIDIA RTX A6000. On paper, it looks excessive. But for local AI, there’s a reason this kind of hardware still makes sense. The A6000 has 48GB of VRAM, while the system has another 1TB of RAM behind it. That gives you a lot more room for large models without immediately running into memory limits. The interesting part is that none of this is cutting-edge hardware. It’s an older workstation being reused for a workload that didn’t exist at this scale when the machine was designed. And that’s becoming one of the best things about Local AI: you don't always need new hardware. Sometimes you just need enough memory.

KyzoroX

69,953 Aufrufe • vor 22 Tagen

ALIBABA GAVE QWEN AWAY FREE, ZUCKERBERG GAVE LLAMA AWAY FREE, AND JENSEN HUANG STILL CHARGES $300 FOR THE 12GB THAT RUNS THEM. THE $80 AMD BOARD HAS 16GB. HE IS TESTING BOTH THIS WEEK AGAINST $200/MO CLAUDE CODE MAX AND $200/MO CHATGPT PRO 00:19 he points at a dead gtx 680 he keeps on the shelf purely for decoration and says "i'm actually really gpu poor" $300 rtx 3060 with 12gb -> $80 bc250 with 16gb -> ubuntu server on both -> 8gb tier, 12 to 16 tier, 24gb ceiling on a four year old 3090 -> qwen against llama at every tier -> tokens per dollar published jensen shipped 12gb on the 3060 in 2021 and consumer vram has barely moved since, alibaba and meta gave the weights away for nothing, the models are free and the only thing left to buy is memory the honest part: he says it himself, this is apples and oranges, and there is not a single benchmark number in this video yet $80 amd bc250 with 16gb gddr6 + $300 rtx 3060 with 12gb + a four year old 3090 with 24gb + ubuntu server + ollama + qwen + llama watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below
2:28

ALIBABA GAVE QWEN AWAY FREE, ZUCKERBERG GAVE LLAMA AWAY FREE, AND JENSEN HUANG STILL CHARGES $300 FOR THE 12GB THAT RUNS THEM. THE $80 AMD BOARD HAS 16GB. HE IS TESTING BOTH THIS WEEK AGAINST $200/MO CLAUDE CODE MAX AND $200/MO CHATGPT PRO 00:19 he points at a dead gtx 680 he keeps on the shelf purely for decoration and says "i'm actually really gpu poor" $300 rtx 3060 with 12gb -> $80 bc250 with 16gb -> ubuntu server on both -> 8gb tier, 12 to 16 tier, 24gb ceiling on a four year old 3090 -> qwen against llama at every tier -> tokens per dollar published jensen shipped 12gb on the 3060 in 2021 and consumer vram has barely moved since, alibaba and meta gave the weights away for nothing, the models are free and the only thing left to buy is memory the honest part: he says it himself, this is apples and oranges, and there is not a single benchmark number in this video yet $80 amd bc250 with 16gb gddr6 + $300 rtx 3060 with 12gb + a four year old 3090 with 24gb + ubuntu server + ollama + qwen + llama watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below

Antid

13,974 Aufrufe • vor 19 Tagen

TWITTER ORDERED THESE EPYC CHIPS AND NEVER TOOK DELIVERY. HE BOUGHT THE ORPHANED BATCH, STACKED 512GB OF RAM AND NOW RUNS DEEPSEEK 671B UNQUANTIZED WHILE ANTHROPIC BILLS $200/MO FOR THE SAME CLASS OF MODEL 00:17 he holds the cpu up and says "these were custom made I think for twitter and then all the twitter stuff happened, so they never got put to use" amd epyc 7v13, the cancelled twitter batch -> supermicro h12ssl-nt, 8 memory channels -> 8x 64gb ddr4-3200, 512gb total -> noctua sp3 cooler -> gutted an old atx case -> the whole model loads into ram, no swap, no quantization his gaming rig has a 9950x3d and 128gb of ddr5 and only two memory channels, this board has eight, so older ddr4 on the epyc moves more data per second than the newer ram on the gaming machine, that's the whole reason cpu inference works at all here the honest part: he expects 1 to 4 tokens per second, which is slower than reading speed, you run this because it holds a 671b model at full precision, not because it's fast amd epyc 7v13 + supermicro h12ssl-nt + 512gb ddr4-3200 across 8 channels + noctua sp3 + deepseek 671b + llama 405b watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below
2:51

TWITTER ORDERED THESE EPYC CHIPS AND NEVER TOOK DELIVERY. HE BOUGHT THE ORPHANED BATCH, STACKED 512GB OF RAM AND NOW RUNS DEEPSEEK 671B UNQUANTIZED WHILE ANTHROPIC BILLS $200/MO FOR THE SAME CLASS OF MODEL 00:17 he holds the cpu up and says "these were custom made I think for twitter and then all the twitter stuff happened, so they never got put to use" amd epyc 7v13, the cancelled twitter batch -> supermicro h12ssl-nt, 8 memory channels -> 8x 64gb ddr4-3200, 512gb total -> noctua sp3 cooler -> gutted an old atx case -> the whole model loads into ram, no swap, no quantization his gaming rig has a 9950x3d and 128gb of ddr5 and only two memory channels, this board has eight, so older ddr4 on the epyc moves more data per second than the newer ram on the gaming machine, that's the whole reason cpu inference works at all here the honest part: he expects 1 to 4 tokens per second, which is slower than reading speed, you run this because it holds a 671b model at full precision, not because it's fast amd epyc 7v13 + supermicro h12ssl-nt + 512gb ddr4-3200 across 8 channels + noctua sp3 + deepseek 671b + llama 405b watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below

Antid

10,074 Aufrufe • vor 12 Tagen

THIS CHINESE BUILDER TURNED 8 RETIRED TESLA P40s INTO A 192GB PRIVATE AI SERVER THAT CAN WORK 5,760 GPU-HOURS EVERY MONTH. 00:06 he holds up one used Tesla P40 while seven more sit behind it, then installs the full stack inside a massive dual-Xeon server chassis. each card carries 24GB of VRAM, giving the system 192GB across eight GPUs for local models, video processing, transcription, private documents and AI agents. the real advantage is parallel work. some cards can serve a local model while the rest generate images, process files and run overnight automation at the same time. eight GPUs running continuously deliver 5,760 GPU-hours every 30 days. rent that workload from the cloud and the meter keeps moving for every minute the server stays online. a $412 monthly AI stack already costs $4,944 a year before serious GPU rental. he bought retired hardware once, kept the data local and built a machine that keeps working after the browser closes.
0:55

THIS CHINESE BUILDER TURNED 8 RETIRED TESLA P40s INTO A 192GB PRIVATE AI SERVER THAT CAN WORK 5,760 GPU-HOURS EVERY MONTH. 00:06 he holds up one used Tesla P40 while seven more sit behind it, then installs the full stack inside a massive dual-Xeon server chassis. each card carries 24GB of VRAM, giving the system 192GB across eight GPUs for local models, video processing, transcription, private documents and AI agents. the real advantage is parallel work. some cards can serve a local model while the rest generate images, process files and run overnight automation at the same time. eight GPUs running continuously deliver 5,760 GPU-hours every 30 days. rent that workload from the cloud and the meter keeps moving for every minute the server stays online. a $412 monthly AI stack already costs $4,944 a year before serious GPU rental. he bought retired hardware once, kept the data local and built a machine that keeps working after the browser closes.

Gipp 🦅

42,332 Aufrufe • vor 2 Monaten

NVIDIA CHARGES $4,000 FOR AN RTX 5090 WITH 32GB. INTEL SELLS THE SAME 32GB FOR $950. HE STACKED TWO INTO 64GB AND KILLED $200/MO CLAUDE CODE AND $200/MO CHATGPT PRO FOR $3 IN ELECTRICITY 00:09 he's been at it since the middle of the night and admits it up front, "I've been testing these pretty much non stop since about 2am today" 2x intel arc pro b70 at $950 each -> 64gb pooled for less than half a 5090 -> asrock taichi lite, both in x8 slots -> ryzen 9600, 64gb ddr5 -> ubuntu 26.04 sees both cards instantly, zero driver hunting -> intel's own stack, not community packages -> mixture of experts models fly nvidia wants $4,000 for 32gb, intel put the same capacity in a card at 23% of that, so a 70b rig went from a $4,000 ticket to $1,900 for double the memory, and the $400 a month altman and amodei charge becomes $3 in electricity the honest part: q8 hits a hard bottleneck on battlemage, bizarre because intel's older alchemist cards were faster at q8 than q4, dense models are rough, and running both cards together has been ugly so far 2x intel arc pro b70 32gb + asrock taichi lite + ryzen 9600 + 64gb ddr5 + ubuntu 26.04 + intel's own inference stack watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below
2:45

NVIDIA CHARGES $4,000 FOR AN RTX 5090 WITH 32GB. INTEL SELLS THE SAME 32GB FOR $950. HE STACKED TWO INTO 64GB AND KILLED $200/MO CLAUDE CODE AND $200/MO CHATGPT PRO FOR $3 IN ELECTRICITY 00:09 he's been at it since the middle of the night and admits it up front, "I've been testing these pretty much non stop since about 2am today" 2x intel arc pro b70 at $950 each -> 64gb pooled for less than half a 5090 -> asrock taichi lite, both in x8 slots -> ryzen 9600, 64gb ddr5 -> ubuntu 26.04 sees both cards instantly, zero driver hunting -> intel's own stack, not community packages -> mixture of experts models fly nvidia wants $4,000 for 32gb, intel put the same capacity in a card at 23% of that, so a 70b rig went from a $4,000 ticket to $1,900 for double the memory, and the $400 a month altman and amodei charge becomes $3 in electricity the honest part: q8 hits a hard bottleneck on battlemage, bizarre because intel's older alchemist cards were faster at q8 than q4, dense models are rough, and running both cards together has been ugly so far 2x intel arc pro b70 32gb + asrock taichi lite + ryzen 9600 + 64gb ddr5 + ubuntu 26.04 + intel's own inference stack watch and save it, musk gave away the agent and moonshot gave away the weights, the full $400 to $25 routing table is in the article below

Antid

38,824 Aufrufe • vor 5 Tagen

the camera being in a tight close up on both ilya and shane for the entirety of this scene, except for the moment when ilya is working up the courage to say he’s in love. it’s like for the whole conversation it’s just the two of them, there’s nobody else who matters, and then for a brief moment the shot widens as ilya considers the implications of the fact he’s in love with shane. the fact that the rest of the world DOES matter and will always be a presence in their relationship. we’ve been held in this moment between the two of them and by widening the shot, that intimacy is broken just for a second as we’re reminded that there is a world beyond the two of them and ilya is still in russia. what he’s doing is incredibly dangerous. then the camera tightens back into a close up as he realises he needs to say it anyway because all that matters is that he’s on the phone with shane and he’s in love with him. it really is just the two of them in this moment and he doesn’t want to let anyone else in.
3:26

the camera being in a tight close up on both ilya and shane for the entirety of this scene, except for the moment when ilya is working up the courage to say he’s in love. it’s like for the whole conversation it’s just the two of them, there’s nobody else who matters, and then for a brief moment the shot widens as ilya considers the implications of the fact he’s in love with shane. the fact that the rest of the world DOES matter and will always be a presence in their relationship. we’ve been held in this moment between the two of them and by widening the shot, that intimacy is broken just for a second as we’re reminded that there is a world beyond the two of them and ilya is still in russia. what he’s doing is incredibly dangerous. then the camera tightens back into a close up as he realises he needs to say it anyway because all that matters is that he’s on the phone with shane and he’s in love with him. it really is just the two of them in this moment and he doesn’t want to let anyone else in.

frances 🏒

294,736 Aufrufe • vor 8 Monaten

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓
1:26

INTEL JUST QUIETLY BUILT THE CHEAPEST PATH TO 128GB OF LOCAL AI VRAM, AND IT BEATS NVIDIA'S DGX SPARK BY 2X FOR THE SAME $4,000 00:11 four Arc Pro B70s racked in one chassis. 32GB of GDDR6 each, $949 MSRP, roughly $1,000 street per card stack four and you get 128GB of VRAM for about $4,000 total. a lab benchmarked the quad against a DGX Spark and a single RTX Pro 6000. the four B70s doubled the Spark or better they trail the Pro 6000, but that card is $10,000. so the real choice is now $4K for 128GB from Intel or $10K for 96GB from NVIDIA the article covers the DGX Spark at $3,999 as the single-desk local AI ceiling. this Intel quad matches the price, beats the memory throughput, and nobody is talking about it yet save this before Intel's VRAM-per-dollar advantage becomes the default homelab build ↓

NO1ennn

139,887 Aufrufe • vor 1 Monat

Elon Musk put 3 ideas in a Wharton thesis and built 2 of them, and the third was Google. 2013, a stage in Norway, and the interviewer says he has 2 minutes before burning the first one on the resume. Zip2 came first maps, yellow pages, white pages, a calendar and it pulled Hearst, Knight Ridder and the New York Times onto the internet before Compaq paid $307M for it. “$400 million,” the interviewer says. “Well, at 300,” Musk says. Then PayPal, largest shareholder, then eBay swallows it and he walks out holding a chunk of that too. Then the thesis comes up, co-written 20 years earlier with a Norwegian classmate, still sitting in an inbox, and the interviewer says he has it on email as proof in case anyone thinks they’re making it up. 3 ideas were in it: index and search the internet, ultracapacitors for storing energy in electric cars, and solar. He shipped 2 and 3 as Tesla and SolarCity. “Unfortunately, of the three, you picked your worst,” the interviewer says, and that year Google was worth $290B while Tesla was worth $19B, and the room laughs, and Musk laughs with it. Last question why will Tesla work when every other electric car company died and his answer contains no vision at all. Critical mass of talent, technology timing, and old electric cars that cost too much with too little range and too little performance, so people did the math and walked away. Value for money, a 40-second reply about whether the product is worth the price. “Okay, thank you,” and the 2 minutes are gone. 12 years later the thesis is still in that inbox, and the battery he kept crossed $1T
3:44

Elon Musk put 3 ideas in a Wharton thesis and built 2 of them, and the third was Google. 2013, a stage in Norway, and the interviewer says he has 2 minutes before burning the first one on the resume. Zip2 came first maps, yellow pages, white pages, a calendar and it pulled Hearst, Knight Ridder and the New York Times onto the internet before Compaq paid $307M for it. “$400 million,” the interviewer says. “Well, at 300,” Musk says. Then PayPal, largest shareholder, then eBay swallows it and he walks out holding a chunk of that too. Then the thesis comes up, co-written 20 years earlier with a Norwegian classmate, still sitting in an inbox, and the interviewer says he has it on email as proof in case anyone thinks they’re making it up. 3 ideas were in it: index and search the internet, ultracapacitors for storing energy in electric cars, and solar. He shipped 2 and 3 as Tesla and SolarCity. “Unfortunately, of the three, you picked your worst,” the interviewer says, and that year Google was worth $290B while Tesla was worth $19B, and the room laughs, and Musk laughs with it. Last question why will Tesla work when every other electric car company died and his answer contains no vision at all. Critical mass of talent, technology timing, and old electric cars that cost too much with too little range and too little performance, so people did the math and walked away. Value for money, a 40-second reply about whether the product is worth the price. “Okay, thank you,” and the 2 minutes are gone. 12 years later the thesis is still in that inbox, and the battery he kept crossed $1T

West Lord

38,476 Aufrufe • vor 1 Monat

We used to buy more VRAM. Now we’re finding ways around the VRAM limit. This little DDR5 SO-DIMM setup is paired with an old NVIDIA Tesla P40 in the video. The P40 is an old datacenter GPU with 24GB of VRAM. By today’s standards, it’s not fast. But combine that with a machine carrying 128GB of system memory, and suddenly you have a very different local AI box. The GPU handles what it’s good at. The system memory gives the model somewhere to go when VRAM runs out. You obviously pay for that with bandwidth and inference speed. But this is the part I find interesting: Local AI is making “how much memory do I have?” almost as important as “how powerful is my GPU?” We’ve spent years chasing faster GPUs. Maybe the next wave of local AI hardware will be about finding smarter ways to use all the memory we already have. More VRAM is still better. But it’s no longer the only way to run a bigger model.
0:27

We used to buy more VRAM. Now we’re finding ways around the VRAM limit. This little DDR5 SO-DIMM setup is paired with an old NVIDIA Tesla P40 in the video. The P40 is an old datacenter GPU with 24GB of VRAM. By today’s standards, it’s not fast. But combine that with a machine carrying 128GB of system memory, and suddenly you have a very different local AI box. The GPU handles what it’s good at. The system memory gives the model somewhere to go when VRAM runs out. You obviously pay for that with bandwidth and inference speed. But this is the part I find interesting: Local AI is making “how much memory do I have?” almost as important as “how powerful is my GPU?” We’ve spent years chasing faster GPUs. Maybe the next wave of local AI hardware will be about finding smarter ways to use all the memory we already have. More VRAM is still better. But it’s no longer the only way to run a bigger model.

KyzoroX

35,554 Aufrufe • vor 4 Tagen

Why Elon didn't want to be CEO: "[Elon] is at core, an engineer and a product guy. He has this great line where he said: "I realized you couldn't be fully in control of the product unless you were also in control of the company." He says he made a moral error, early in Tesla, where he was trying to have his cake and eat it too. He wanted to control the company without running the company. And that was the 2002 to 2008 era, where Tesla was just off to a really messy start. He was providing the funding. He was chairman of the board. But Martin Eberhard was CEO. Eventually, when Tesla was on the verge of death in 2008....Elon was pushed into the position of: "I have to be CEO. I don't want to be. It comes with a lot of chores. It comes with a lot of responsibilities. But if I want this company to be successful, I have to fully internalize and take responsibility for it." And that's what he did, even though he was also in the same position at SpaceX. The fact that these companies are improbable, iconic, and that he funded and led them both in parallel...it's like running a two minute mile twice at the same time. It is such a higher degree of difficulty than most people can conceive of, and the fact that it worked is still unbelievable."
4:24

Why Elon didn't want to be CEO: "[Elon] is at core, an engineer and a product guy. He has this great line where he said: "I realized you couldn't be fully in control of the product unless you were also in control of the company." He says he made a moral error, early in Tesla, where he was trying to have his cake and eat it too. He wanted to control the company without running the company. And that was the 2002 to 2008 era, where Tesla was just off to a really messy start. He was providing the funding. He was chairman of the board. But Martin Eberhard was CEO. Eventually, when Tesla was on the verge of death in 2008....Elon was pushed into the position of: "I have to be CEO. I don't want to be. It comes with a lot of chores. It comes with a lot of responsibilities. But if I want this company to be successful, I have to fully internalize and take responsibility for it." And that's what he did, even though he was also in the same position at SpaceX. The fact that these companies are improbable, iconic, and that he funded and led them both in parallel...it's like running a two minute mile twice at the same time. It is such a higher degree of difficulty than most people can conceive of, and the fact that it worked is still unbelievable."

Ti Morse

47,497 Aufrufe • vor 4 Monaten

SONY SHIPS THIS APU IN A $200 PS5. BITCOIN OPERATIONS DUMPED IT ON EBAY FOR $40. HE 3D PRINTED A CASE OVERNIGHT AND KILLED $439 A MONTH IN ANTHROPIC AND OPENAI BILLS 00:34 he turns the board over and says "this was actually meant for bitcoin mining originally, and this uses ps5 adjacent hardware for the apu" $80 bc250 off ebay -> one 8 pin connector, no pcie, no motherboard -> $50 flex itx 500w psu -> 20 hour ASA print for the case -> blow four years of mining dust out with an air compressor -> 16gb gddr6 unified, ollama up in 4 minutes sony sold 117 million ps5s on this silicon, bitcoin operations bought the mining variant by the pallet, ethereum's merge stranded all of it, and now the same oberon apu that renders spider-man runs a local coding model for the price of a dinner the honest part: it arrived filthy, the compressor barely touched the dust, and you need a 3d printer before the board does anything at all $80 amd bc250 + $50 flex itx 500w + 20h ASA print + oberon apu with 16gb gddr6 + ubuntu + ollama watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below
1:47

SONY SHIPS THIS APU IN A $200 PS5. BITCOIN OPERATIONS DUMPED IT ON EBAY FOR $40. HE 3D PRINTED A CASE OVERNIGHT AND KILLED $439 A MONTH IN ANTHROPIC AND OPENAI BILLS 00:34 he turns the board over and says "this was actually meant for bitcoin mining originally, and this uses ps5 adjacent hardware for the apu" $80 bc250 off ebay -> one 8 pin connector, no pcie, no motherboard -> $50 flex itx 500w psu -> 20 hour ASA print for the case -> blow four years of mining dust out with an air compressor -> 16gb gddr6 unified, ollama up in 4 minutes sony sold 117 million ps5s on this silicon, bitcoin operations bought the mining variant by the pallet, ethereum's merge stranded all of it, and now the same oberon apu that renders spider-man runs a local coding model for the price of a dinner the honest part: it arrived filthy, the compressor barely touched the dust, and you need a 3d printer before the board does anything at all $80 amd bc250 + $50 flex itx 500w + 20h ASA print + oberon apu with 16gb gddr6 + ubuntu + ollama watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below

Antid

35,778 Aufrufe • vor 21 Tagen

JENSEN HUANG STRIPPED NVLINK OUT OF CONSUMER CARDS IN 2021 TO PROTECT A $30K PRODUCT LINE. JIM KELLER PUT IT BACK IN A $1,400 CARD. HE MESHED TWO OFF A SINGLE PSU AND RUNS KIMI K3 FOR $6/MONTH 00:13 he holds up the green cable bundle, looks at the camera and says "we're not hooking team green up to these" 2 blackhole p150a for $2,800 -> skip the adapter chain entirely -> two 600w cables direct off one seasonic -> qsfp-dd 800g mesh card to card -> the pcie slot goes idle after model load -> kimi k3 at full 1m context for $6/month nvidia's whole $30k moat is the interconnect, keller shipped it on a card that costs 4.6% of an h100, tenstorrent's queue hit 11 weeks and the pcie bus that nvidia optimizes around stopped mattering in this build entirely the honest part: the software stack is 6 months behind cuda, you will lose a weekend to driver builds before the first token lands 2x tenstorrent blackhole p150a + qsfp-dd 800g + 1000w seasonic + ubuntu 26.04 + neo4j + kimi k3 watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below
1:04

JENSEN HUANG STRIPPED NVLINK OUT OF CONSUMER CARDS IN 2021 TO PROTECT A $30K PRODUCT LINE. JIM KELLER PUT IT BACK IN A $1,400 CARD. HE MESHED TWO OFF A SINGLE PSU AND RUNS KIMI K3 FOR $6/MONTH 00:13 he holds up the green cable bundle, looks at the camera and says "we're not hooking team green up to these" 2 blackhole p150a for $2,800 -> skip the adapter chain entirely -> two 600w cables direct off one seasonic -> qsfp-dd 800g mesh card to card -> the pcie slot goes idle after model load -> kimi k3 at full 1m context for $6/month nvidia's whole $30k moat is the interconnect, keller shipped it on a card that costs 4.6% of an h100, tenstorrent's queue hit 11 weeks and the pcie bus that nvidia optimizes around stopped mattering in this build entirely the honest part: the software stack is 6 months behind cuda, you will lose a weekend to driver builds before the first token lands 2x tenstorrent blackhole p150a + qsfp-dd 800g + 1000w seasonic + ubuntu 26.04 + neo4j + kimi k3 watch and save it, then kill your $439 stack this weekend, kimi does the same work at $19 flat and the whole map is in the article below

Antid

25,925 Aufrufe • vor 22 Tagen

Chris Bledsoe says he was shown by a celestial being he calls 'The Lady' the entire Iranian-Israeli conflict. He wrote it down at the request of someone at the Pentagon, and it was hand-delivered to two generals. “She showed it to me in a vision, and what I saw I wrote down at the request of someone at the Pentagon, and it was hand-delivered to two generals at the Pentagon. That was in 2012. I saw all of this, the entire Iranian-Israeli conflict.” He says she returned at Easter 2019, when he was in a wheelchair with rheumatoid arthritis. “She told me that trouble was coming. And that the suffering of humanity will become too great. And that they will intervene to help humanity. They will awaken us to their presence.” He later added the warning he says she gave him: “When you see Israel and Iran starting to fire missiles at each other, beware, because if it develops enough,” she showed him “a vision of Israel being heavily bombed by Iran. So bad that they launched six nuclear missiles. I saw four of them heading towards Iran. I saw two heading towards Syria. Then the sky was completely illuminated by celestial bodies, and then darkness prevailed everywhere.” That is the account he gave on camera. He presents it as a 2012 written report sent into the Pentagon, then restated at Easter 2019 before the later missile exchanges between Israel and Iran.
2:39

Chris Bledsoe says he was shown by a celestial being he calls 'The Lady' the entire Iranian-Israeli conflict. He wrote it down at the request of someone at the Pentagon, and it was hand-delivered to two generals. “She showed it to me in a vision, and what I saw I wrote down at the request of someone at the Pentagon, and it was hand-delivered to two generals at the Pentagon. That was in 2012. I saw all of this, the entire Iranian-Israeli conflict.” He says she returned at Easter 2019, when he was in a wheelchair with rheumatoid arthritis. “She told me that trouble was coming. And that the suffering of humanity will become too great. And that they will intervene to help humanity. They will awaken us to their presence.” He later added the warning he says she gave him: “When you see Israel and Iran starting to fire missiles at each other, beware, because if it develops enough,” she showed him “a vision of Israel being heavily bombed by Iran. So bad that they launched six nuclear missiles. I saw four of them heading towards Iran. I saw two heading towards Syria. Then the sky was completely illuminated by celestial bodies, and then darkness prevailed everywhere.” That is the account he gave on camera. He presents it as a 2012 written report sent into the Pentagon, then restated at Easter 2019 before the later missile exchanges between Israel and Iran.

Interstellar

39,540 Aufrufe • vor 8 Tagen

a shape with no inside. he filled it with water anyway pour water in and it stops almost immediately. the air has nowhere to escape, so it just sits there blocking you. tilt it and you get a little more in, then it blocks again so he put the whole thing in a vacuum chamber turn it on and the bottle starts bubbling. that's the air being pulled out through the neck, leaving as close to nothing inside as he can get then he lets the pressure back in, and the water rushes up into the empty space on its own still not full. so he runs it again, rarefying the smaller pocket of air that's left, and again after that here's the part that breaks your head: for a shape to have volume, it has to split the world in two. a ball does that. stretch it however you want, there's always a world inside and a world outside a Klein bottle has no such line. follow its surface and you never cross a boundary, never pass through a wall, never end up anywhere that isn't the same side you started on the inside is the outside. so there's nothing there to fill he filled it anyway that's the same shape as the room below. no plot, no payoff, just a question your brain won't drop -> can a thing with no inside hold anything at all two videos, two impossible questions, 20 million views between them. Paone broke down why this format works in the article underneath save this. the most watched thing today was a shape that shouldn't be able to hold anything, holding water
2:39

a shape with no inside. he filled it with water anyway pour water in and it stops almost immediately. the air has nowhere to escape, so it just sits there blocking you. tilt it and you get a little more in, then it blocks again so he put the whole thing in a vacuum chamber turn it on and the bottle starts bubbling. that's the air being pulled out through the neck, leaving as close to nothing inside as he can get then he lets the pressure back in, and the water rushes up into the empty space on its own still not full. so he runs it again, rarefying the smaller pocket of air that's left, and again after that here's the part that breaks your head: for a shape to have volume, it has to split the world in two. a ball does that. stretch it however you want, there's always a world inside and a world outside a Klein bottle has no such line. follow its surface and you never cross a boundary, never pass through a wall, never end up anywhere that isn't the same side you started on the inside is the outside. so there's nothing there to fill he filled it anyway that's the same shape as the room below. no plot, no payoff, just a question your brain won't drop -> can a thing with no inside hold anything at all two videos, two impossible questions, 20 million views between them. Paone broke down why this format works in the article underneath save this. the most watched thing today was a shape that shouldn't be able to hold anything, holding water

Banff

2,567,785 Aufrufe • vor 1 Monat

TCG Outpost explains why he’s betting on Dragon Ball cards “There's a massive thesis right now for all of these. There are only 42 Dragon Ball mangas and there’s only 42 of these cards” “Each one of these cards is the literal cover of the mangas translated into card form. They're the actual covers of the Dragon Ball manga” “My calculations and also people in the community say that there are probably less than 250 to 300 of each card ever printed and there's going to be less than 250 that ever exist of each individual card” “I bought this one for $76 raw. I graded it. It costed me $35 to grade it and now it's worth $2,000. I bought these two for $1,800 each and they’re both worth $4,000 now” “This is called the Kobe Goku because it has number 24 right here. Kobe Goku bought for $2,200, currently $5,000” Rasmr: “These can go way higher man. The DBZ ones can go higher” TCG Outpost: “There's only like 200 to 250 that are ever going to be printed of them and they're the literal covers of the manga. It's directly tied to the IP and it’s manga and anime season right now. So it's the move for sure”
2:44

TCG Outpost explains why he’s betting on Dragon Ball cards “There's a massive thesis right now for all of these. There are only 42 Dragon Ball mangas and there’s only 42 of these cards” “Each one of these cards is the literal cover of the mangas translated into card form. They're the actual covers of the Dragon Ball manga” “My calculations and also people in the community say that there are probably less than 250 to 300 of each card ever printed and there's going to be less than 250 that ever exist of each individual card” “I bought this one for $76 raw. I graded it. It costed me $35 to grade it and now it's worth $2,000. I bought these two for $1,800 each and they’re both worth $4,000 now” “This is called the Kobe Goku because it has number 24 right here. Kobe Goku bought for $2,200, currently $5,000” Rasmr: “These can go way higher man. The DBZ ones can go higher” TCG Outpost: “There's only like 200 to 250 that are ever going to be printed of them and they're the literal covers of the manga. It's directly tied to the IP and it’s manga and anime season right now. So it's the move for sure”

Jack

103,357 Aufrufe • vor 3 Monaten