1
00:00:00,480 --> 00:00:08,320
$4,000. That is what these modified 48 gigabyte

2
00:00:05,520 --> 00:00:13,759
RTX 4090s from China are going for. Personally, I love how hot and loud they

3
00:00:11,120 --> 00:00:17,760
get. They're great. And the best part, aside from the inflated price that I

4
00:00:15,679 --> 00:00:23,920
paid that makes me feel like a big shot, is the fact that it loses in nearly

5
00:00:20,640 --> 00:00:25,840
every benchmark against a regular 4090

6
00:00:23,920 --> 00:00:31,279
gaming card. In case it wasn't obvious by this point, yes, this thing makes

7
00:00:28,240 --> 00:00:33,040
absolutely no sense for gamings, but

8
00:00:31,279 --> 00:00:38,960
there are tons of listings for them online and even positive reviews. Maybe

9
00:00:36,239 --> 00:00:46,480
they're great for productivity. Nope. Oh, of course, large language

10
00:00:43,040 --> 00:00:48,879
models love VRAM. The more the better.

11
00:00:46,480 --> 00:00:54,879
And not only are 5090s hard to get your hands on, but they have just 32 gigs of

12
00:00:51,920 --> 00:01:00,480
memory, which pales in comparison to this monster. But demonstrating what

13
00:00:58,079 --> 00:01:04,799
makes these cards so desirable that they're worth dismantling and then

14
00:01:02,640 --> 00:01:10,400
remanufacturing an already expensive card is tricky. See, if we run our

15
00:01:07,200 --> 00:01:13,840
regular AI benchmarks, our regular 4090

16
00:01:10,400 --> 00:01:16,159
here actually wins again. But under the

17
00:01:13,840 --> 00:01:23,119
right conditions, this thing should crush not only a regular old 24 gig

18
00:01:19,600 --> 00:01:25,680
4090, but even beat a 5090. And I'm

19
00:01:23,119 --> 00:01:31,280
going to show you after I generate a segue to our sponsor,

20
00:01:31,280 --> 00:01:37,680
Threat Locker. Threat Locker is hosting a free webinar series all about how to

21
00:01:35,680 --> 00:01:41,680
secure your IT environment. Just click our link in the video description to get

22
00:01:39,280 --> 00:01:45,640
caught up on any past sessions and to register for the next one.

23
00:01:52,560 --> 00:01:58,079
Before we get into our live drag race, I need to figure out what the heck it is

24
00:01:56,240 --> 00:02:01,200
we actually bought here. Because the closer I look at this thing, the more

25
00:01:59,680 --> 00:02:05,680
questions it raises. See, on the surface, it's pretty straightforward. I

26
00:02:02,960 --> 00:02:11,440
mean, it's an RTX 4090, and they probably desoldered the 24 gigs of DDDR

27
00:02:08,479 --> 00:02:16,080
6X and replaced it with 48 gigs of DDDR 6X, except for one small problem. See,

28
00:02:13,520 --> 00:02:20,560
it's got a blower style two slot cooler, which allegedly NVIDIA does not allow

29
00:02:18,959 --> 00:02:24,560
its gaming partners to build because they're worried that cards like this,

30
00:02:22,400 --> 00:02:29,120
which can be packed into workstations or servers, would cannibalize their ability

31
00:02:26,720 --> 00:02:33,280
to sell enterprise and workstation cards. But it also doesn't seem to be

32
00:02:31,280 --> 00:02:39,360
one of NVIDIA's authorized professional card designs. All the imagery that I can

33
00:02:35,680 --> 00:02:41,760
find of the RTX A6000 ADA has the same

34
00:02:39,360 --> 00:02:45,519
cutout PCB at the back so that it can pull air both from the front and the

35
00:02:43,920 --> 00:02:50,319
back before exhausting it out the back of the case. So, this seems to be a

36
00:02:47,440 --> 00:02:55,040
unique cooler and PCB combination that some Chinese manufacturer or

37
00:02:52,400 --> 00:03:02,560
manufacturers, probably without any authorization from NVIDIA, has created

38
00:02:57,840 --> 00:03:05,200
in order to turn RTX 4090 and 4090ds

39
00:03:02,560 --> 00:03:09,599
into AI compute cards. And by turn them into, I really do mean like full

40
00:03:07,440 --> 00:03:13,840
Frankenstein's monster. We found this article on Techbot that appears to show

41
00:03:11,840 --> 00:03:19,200
cards that look an awful lot like these ones being validated on test benches

42
00:03:16,239 --> 00:03:23,760
next to pallets of regular gaming cards that appear to be headed for

43
00:03:21,040 --> 00:03:28,560
disassembly. And actually we can see here that yeah the initial hypothesis of

44
00:03:26,879 --> 00:03:32,480
desoldering the memory and then resoldering memory with double the

45
00:03:30,080 --> 00:03:39,840
capacity was obviously wrong because unlike any gaming RTX490 design we see

46
00:03:36,319 --> 00:03:42,239
ah yes memory packages on the back of

47
00:03:39,840 --> 00:03:47,040
the board. So to achieve the doubling of capacity they're using double the number

48
00:03:44,480 --> 00:03:50,799
of packages just like one of NVIDIA's professional cards would. It really goes

49
00:03:48,799 --> 00:03:55,040
to show how much NVIDIA charges their enterprise customers for their GPUs that

50
00:03:53,120 --> 00:03:59,760
it's more economical to buy gaming cards, disassemble them, discard the

51
00:03:57,760 --> 00:04:04,000
PCBs, and then go and source additional memory and remanufacture the card. Not

52
00:04:02,319 --> 00:04:08,560
that they discard the PCBs. I mean, if you've ever wondered where the heck all

53
00:04:05,599 --> 00:04:13,760
of those uh chipless 4090s and stuff that you see on eBay come from, yo,

54
00:04:11,280 --> 00:04:20,000
those are funky thermal pads. They look so dry. really clean layout and massive

55
00:04:17,519 --> 00:04:23,360
power delivery. This is key because not only does NVIDIA charge their enterprise

56
00:04:21,840 --> 00:04:27,520
customers an arm and a leg for the privilege of using their products, but

57
00:04:25,360 --> 00:04:33,280
they typically deliver them with lower power profiles. This does improve

58
00:04:30,080 --> 00:04:35,280
thermals and longevity, but it also

59
00:04:33,280 --> 00:04:40,160
harms performance. So, these remanufactured cards will be more

60
00:04:37,520 --> 00:04:43,840
affordable and also more performant in some cases than the official NVIDIA

61
00:04:42,240 --> 00:04:48,240
solution. That assumes, of course, though, that we can keep the thermals

62
00:04:45,520 --> 00:04:52,479
under control with this wimpy dual slot cooler. To be clear, I'm not attacking

63
00:04:50,160 --> 00:04:56,400
the quality. That appears to be a fat vapor chamber, which is going to help a

64
00:04:54,160 --> 00:05:02,400
lot. It's just not a lot of metal to cool 450 watts of GPU. Hey, this

65
00:05:00,720 --> 00:05:05,759
explains the observation that you guys made about the performance being

66
00:05:03,840 --> 00:05:09,680
crappier, though. If you've got twice as many memory chips, we're just eating up

67
00:05:08,000 --> 00:05:15,520
some of our limited power profile for the whole board. So, yeah. Cool. Mystery

68
00:05:12,960 --> 00:05:21,039
solved. All right, let's fire up GPUZ. Have a look at what the heck this thing

69
00:05:17,360 --> 00:05:24,000
is. RTX 4090. So, it's not a D. It's too

70
00:05:21,039 --> 00:05:27,919
bad. I love the D. I don't actually love the D. It's smaller and less powerful.

71
00:05:25,840 --> 00:05:30,800
Micron memory. That's consistent with what I saw when I was taking apart the

72
00:05:29,440 --> 00:05:34,240
card. We have no way of knowing if it's new or if it was, you know, pulled off

73
00:05:32,639 --> 00:05:38,080
of gaming cards. If anything, I would expect that it was. But hey, it's

74
00:05:36,080 --> 00:05:42,400
Micron. This is interesting. They obviously had to develop their own VIOs

75
00:05:40,400 --> 00:05:47,600
for these cards. So, they just set the sub vendor to NVIDIA, unless NVIDIA is

76
00:05:46,080 --> 00:05:51,600
complicit in the creation of these, but man, do I ever doubt that. And yeah,

77
00:05:49,840 --> 00:05:55,360
realistically, other than having double the memory, it looks like a pretty

78
00:05:53,360 --> 00:06:01,199
normal 4090. Do we have firm mark on here? Like, can we just kind of see what

79
00:05:57,199 --> 00:06:03,919
happens when we load it? Hi, buddy.

80
00:06:01,199 --> 00:06:08,560
Yeah, I I see you there. You don't got to yell about it. Right. in firmark GPU

81
00:06:06,479 --> 00:06:13,680
is getting less than 400 watts because we have so much memory on this thing.

82
00:06:11,039 --> 00:06:17,199
PCIe is operating at Gen 4 by6, so that's operating normally. Not something

83
00:06:15,199 --> 00:06:21,760
I would necessarily take for granted. Wow, is that ever loud. 5,000

84
00:06:20,400 --> 00:06:24,000
RPM.

85
00:06:24,000 --> 00:06:31,120
Woo! Do we have afterurner on here? Oh, Norton 360 for gamers. Yeah, comes with

86
00:06:29,199 --> 00:06:36,160
afterurners for overclocking. For overclocking my antivirus. MSI, you

87
00:06:33,919 --> 00:06:39,759
already sold me a GPU. You don't have to bundle it with Norton. Well, that was

88
00:06:37,759 --> 00:06:43,759
anticlimactic. No power level adjustment, so we're stuck with what we

89
00:06:41,600 --> 00:06:48,880
got. But hey, at least it's a nice GPU temperature that should stay under

90
00:06:45,520 --> 00:06:50,880
control even in a closed chassis. But

91
00:06:48,880 --> 00:06:54,800
barely, especially if you have these packed next to each other like they

92
00:06:52,800 --> 00:06:58,720
appear to be designed to do. Dude, you can even see the PF cap reason the

93
00:06:56,960 --> 00:07:02,000
entire time was power. If we could increase the power limit of this card,

94
00:07:00,400 --> 00:07:05,840
it could go a little better. For our benchmark, we've set up Olama, our

95
00:07:03,919 --> 00:07:09,639
locally deployed AI model runner to model Gemma 3.27B-IT-Q4_0.

96
00:07:10,560 --> 00:07:17,840
Right now, all we got to do is add our prompts and go. This is on our regular

97
00:07:14,800 --> 00:07:19,840
4090, and this is the Q4. The percentage

98
00:07:17,840 --> 00:07:23,759
of this stuff that's just outright wrong is wild. Lionus is known for his

99
00:07:22,080 --> 00:07:28,000
energetic, enthusiastic, and often self-deprecating personality. He's

100
00:07:25,599 --> 00:07:33,360
transparent about mistakes and isn't afraid to admit when things go wrong,

101
00:07:31,039 --> 00:07:38,240
which they often do in their experimental builds. He's become a

102
00:07:35,759 --> 00:07:45,919
trusted voice in the tech community due to his honesty and accessibility. That's

103
00:07:40,800 --> 00:07:50,479
all wrong. How tall his line is so 6' 3

104
00:07:45,919 --> 00:07:52,720
in. Why does it think you're so tall?

105
00:07:50,479 --> 00:07:57,680
Well, it's thinking horizontal, but it knows that my height is noticeable

106
00:07:55,440 --> 00:08:01,039
compared to other people on camera. It also pulled this from Wikipedia. My

107
00:07:59,199 --> 00:08:04,560
height is correct on Wikipedia. Let's see what the sources. I don't get this.

108
00:08:02,800 --> 00:08:08,319
It cites Wikipedia as a source, but Wikipedia has my height right. Does it

109
00:08:06,319 --> 00:08:11,680
though? Yeah, I'm pretty sure. I don't see a height. I swear my height used to

110
00:08:10,240 --> 00:08:17,840
be here. Well, now we know why it's getting it wrong then because that's not on here. A son and two daughters. Yeah,

111
00:08:15,680 --> 00:08:21,520
that's correct. It does not list your height. So now we

112
00:08:19,599 --> 00:08:28,120
know why it is wrong. The first time you run it, it can be a little bit slow. So

113
00:08:23,840 --> 00:08:28,120
I'll ask it something. Um,

114
00:08:28,800 --> 00:08:36,719
let's see if it knows. I It might They know. Yes, Nicholas, known online as

115
00:08:34,320 --> 00:08:41,200
Nicholas Plof Visuals, does own and operate a display at the Mall of America

116
00:08:39,039 --> 00:08:44,959
in Minneapolis, Minnesota. Yeah, that's not my I don't have a website called

117
00:08:42,479 --> 00:08:51,200
Nicholasplof.com/chromatic. Yes, Nick from Lionus Tech Tips does

118
00:08:48,640 --> 00:08:55,040
co-own a display at the Mall of America. It's the same one mentioned previous and

119
00:08:53,200 --> 00:08:59,440
that clarifies which Nick PL we're talking about. You're his son. This just

120
00:08:56,959 --> 00:09:04,480
completely made this up. Yeah, I love AI. It's great. So, the answer is yes.

121
00:09:01,600 --> 00:09:08,399
Both Nicholas Plof senior and Nick Plof from LT are owners of the chromatic I

122
00:09:06,720 --> 00:09:11,680
got to get, you know, whatever dividends I'm owed from owning this chromatic

123
00:09:09,920 --> 00:09:16,560
motion display. This is a video about the display, so we should probably click

124
00:09:13,920 --> 00:09:20,160
it. not available anymore. I think you made all of this up. You're absolutely

125
00:09:18,399 --> 00:09:22,959
right to question me. My apologize. I seem to have completely fabricated that

126
00:09:21,839 --> 00:09:26,959
information. I'm still under development. There is no evidence that

127
00:09:25,440 --> 00:09:30,720
either Nicholas Blof, the artist, or Nick Bl from LT, owns or operates a

128
00:09:29,360 --> 00:09:35,120
display at the Mall of America. Why is it so hung up on the Mall of America?

129
00:09:32,480 --> 00:09:39,839
Okay, but I still want to know if Nick Blof owns a display. You are absolutely

130
00:09:37,760 --> 00:09:45,680
right to push back and clarify. I got completely sidetracked by the display

131
00:09:42,640 --> 00:09:48,480
meaning an art installation. Nicholas PL

132
00:09:45,680 --> 00:09:53,360
frequently shows off his display wall. That's not true. What are you talking

133
00:09:50,560 --> 00:09:56,160
about? I got I do own several displays, but I don't have an entire All of this

134
00:09:54,720 --> 00:09:59,839
is besides the point. We're supposed to be benchmarking these. Okay, so we'll

135
00:09:57,920 --> 00:10:07,440
write the same prompt. These are kind of hot and ready now. So, uh, how do I

136
00:10:02,720 --> 00:10:09,200
build a computer? Three, two, one.

137
00:10:07,440 --> 00:10:15,600
Whoa. Oh wow. Whoa. You're getting crushed,

138
00:10:12,720 --> 00:10:20,079
brother. This will So Q4 isn't even the bad one. So this is still using less

139
00:10:18,240 --> 00:10:24,240
than 24 gigs of VRAM. Like actually, let's open the hardware information. Or

140
00:10:21,839 --> 00:10:29,279
you hear my GPU going? I do. I do. She's going, bud. Like I'm using not fully 24

141
00:10:26,880 --> 00:10:33,839
gigs. I'm using Yeah. 20.2 out of 24 gigs. What's your VRAM usage at? 21

142
00:10:31,680 --> 00:10:37,519
gigs. So yours is just faster right now. You know what? I think yours might have

143
00:10:35,360 --> 00:10:41,760
just kind of hiccuped at the beginning, though. So we both got slightly

144
00:10:39,440 --> 00:10:46,079
different answers which we would expect even running the same model and asking

145
00:10:43,440 --> 00:10:50,640
the same question that is typical. They do contain a lot of the same tips. What

146
00:10:48,959 --> 00:10:54,640
we want to know is the performance. So we need to know how many tokens per

147
00:10:52,320 --> 00:10:59,760
second. You got slightly more. You got 40.43 response tokens per second. I got

148
00:10:56,959 --> 00:11:02,959
40.06. Okay. Realistically it was about the same then other than that little

149
00:11:01,519 --> 00:11:06,240
hiccup at the beginning while his spooled up. Let's try one more time just

150
00:11:04,640 --> 00:11:13,279
for loss. One more time. Sure. Write a short story, no more than500 words,

151
00:11:10,000 --> 00:11:15,519
about Nicholas Plof discovering his love

152
00:11:13,279 --> 00:11:23,040
of displays. We should specify Nicholas Plof from LT. Okay. Not from the Mall of

153
00:11:18,320 --> 00:11:25,279
America. 1 2 3 go.

154
00:11:23,040 --> 00:11:28,480
The gradient of wonder. The ghost in the pixels. Oh, I like your title better.

155
00:11:26,959 --> 00:11:34,800
That's way cooler than the gradient of wonder. He wasn't born chasing perfect

156
00:11:31,760 --> 00:11:36,720
blacks or pixel densities.

157
00:11:34,800 --> 00:11:39,720
He wasn't even particularly good with electronics.

158
00:11:39,760 --> 00:11:46,320
You've really taken to this, haven't you? Lionus said, walking in on Nicholas

159
00:11:43,839 --> 00:11:51,839
painstakingly adjusting the gamma curve on her particularly finicky monitor.

160
00:11:48,800 --> 00:11:54,000
It's fascinating, surprised by some

161
00:11:51,839 --> 00:11:58,320
enthusiasm. He wasn't just reviewing a monitor. He was sharing his love of

162
00:11:56,000 --> 00:12:03,440
displays with the world. And in that moment, he knew he was exactly where he

163
00:12:00,640 --> 00:12:09,120
was meant to be. Wow. He was simply a man captivated by the wonder of light.

164
00:12:06,560 --> 00:12:14,079
It's actually pretty good Okay, but how many per second? 40.1. I'm at

165
00:12:12,240 --> 00:12:17,360
39.68. Okay, so I actually get a little bit more performance because a little

166
00:12:15,519 --> 00:12:25,279
bit. We're about to ratchet this up a notch by switching over to uh Q8_0.

167
00:12:22,079 --> 00:12:27,600
This theoretically will not fit in

168
00:12:25,279 --> 00:12:31,839
Plof's VRAM, which doesn't mean he can't run it. It just means that it's going to

169
00:12:29,680 --> 00:12:36,160
spill out into system memory which should result in marketkedly different

170
00:12:33,920 --> 00:12:41,360
performance. Yeah. Test prompt. Really? Yes. I want to see what it does. Fine.

171
00:12:38,639 --> 00:12:45,440
He smiled. He still loved wood. Still enjoyed the satisfaction of creating

172
00:12:43,120 --> 00:12:50,480
something tangible. It's true. Yours is done though. My Look at how my even the

173
00:12:47,760 --> 00:12:55,519
test prompt. Wa. This is a much larger model though.

174
00:12:53,519 --> 00:13:00,160
So theoretically the quality of its responses should be greater. I can't

175
00:12:58,240 --> 00:13:06,399
believe how much faster that ran on mine. Right. Your system memory usage is

176
00:13:02,880 --> 00:13:11,519
gig huge. So total 40 gigs and I'm using

177
00:13:06,399 --> 00:13:15,040
a total of about 45, but most of that 33

178
00:13:11,519 --> 00:13:17,760
gigs of it is my GPU. So this model

179
00:13:15,040 --> 00:13:21,279
simply wouldn't fit in any consumer GPU, including the 5090. Okay, that was a

180
00:13:19,600 --> 00:13:24,399
test prompt. Let's try one more actual prompt. Let's Should we try one of our

181
00:13:23,120 --> 00:13:29,120
previous prompts just to see if the quality is a little bit better? Sure. Let's I want to know if it knows who the

182
00:13:27,440 --> 00:13:34,120
Nicholas Plof is and whether he owns a display or not. 3 2 1 go.

183
00:13:35,360 --> 00:13:42,160
Yeah, yours is spitting out like lines while mine is going word by word. Some

184
00:13:40,320 --> 00:13:46,480
of this Where is it getting the woodworking stuff from? I don't know. I

185
00:13:44,480 --> 00:13:49,920
do know some woodworking, but that's like a high school skill. That is not

186
00:13:48,160 --> 00:13:54,079
I've never owned a woodworking shop. Okay, here's Nicholas's display wall. It

187
00:13:52,240 --> 00:13:59,199
has an actual reference list. It's not available. It's just making they're making fake links. It's done, but it's

188
00:13:56,959 --> 00:14:02,160
like tiny by comparison. Let's see your prompt. So, yours is way more detailed

189
00:14:00,560 --> 00:14:07,279
than mine, too. Like, I have like a little bit. It's similar.

190
00:14:05,040 --> 00:14:11,519
And it specifically, he upgraded to a Samsung Odyssey Neo G9. I did not do

191
00:14:09,199 --> 00:14:14,959
that. No, but that was an actual thing. We made a video about it. It was. Yeah.

192
00:14:13,279 --> 00:14:19,920
Do you want to see if that YouTube link is an actual video this time? No, it's

193
00:14:17,279 --> 00:14:27,440
not. No. Response tokens per second 26 and a 4.76. Literally five times the

194
00:14:24,079 --> 00:14:29,440
performance. It's still AI gobbledegook,

195
00:14:27,440 --> 00:14:33,040
but it's doing it way faster. Way faster. Kayla, you want to try image

196
00:14:31,839 --> 00:14:38,320
generation? What do you want to start with? YouTube host owning or fixing a

197
00:14:35,519 --> 00:14:42,480
computer. Oh, there goes your card. All right, she's going. So, what do you do

198
00:14:40,639 --> 00:14:48,399
with this after? Do you keep it? This is That's what you can use to upgrade from

199
00:14:45,360 --> 00:14:51,440
your 3080. You don't need a 5090. You

200
00:14:48,399 --> 00:14:53,199
can use a 48 gig 4090. you'll have even

201
00:14:51,440 --> 00:14:57,600
more VRAM. I don't need more VRAM. We'll talk about

202
00:14:55,600 --> 00:15:02,720
that in a little bit more detail later, but more VRAM is not necessarily more

203
00:15:00,320 --> 00:15:06,320
better for especially certain workloads. Yours is going faster. I'll tell you

204
00:15:03,920 --> 00:15:11,120
that much. Not that much faster. No, that thing screams though. Okay. How's

205
00:15:08,079 --> 00:15:13,440
my VR use though? Wow. I am using 33

206
00:15:11,120 --> 00:15:17,680
gigs of VRAM though. You're at I'm not Wow. Like 12. It's not even using

207
00:15:16,000 --> 00:15:21,839
everything you have. Yeah. What's interesting is mine is using the same

208
00:15:20,079 --> 00:15:24,720
amount of system memory as you too though. Yeah, I'm using a little bit

209
00:15:23,199 --> 00:15:28,959
more. I'm using like Yeah, hold on. Maybe I left some Lama stuff open in the

210
00:15:27,040 --> 00:15:32,480
back. This is weird. Our performance is about the same cuz and which makes sense

211
00:15:30,959 --> 00:15:36,240
cuz our parameters are all the same and we shouldn't be using more than the

212
00:15:34,399 --> 00:15:42,480
amount of memory that we both have, but my RAM use is way higher than his.

213
00:15:40,079 --> 00:15:46,720
Well, these are fun. Sure, that monitor looks like Apple

214
00:15:44,240 --> 00:15:50,720
designed it. And it's backwards for like the stand is going into the screen. I

215
00:15:48,959 --> 00:15:54,639
love AI. It's so good. I like how devious this guy looks. Look at him go.

216
00:15:52,959 --> 00:15:58,880
This one's not bad. Other than that mouse would not fit any human hand. It

217
00:15:57,120 --> 00:16:02,560
might fit this guy's hand. His fingers though. He's got an extra finger. Oh,

218
00:16:00,480 --> 00:16:05,839
yeah. Yeah. I like how I got a cartoon. Oh, that's cool. You didn't? Yeah.

219
00:16:04,320 --> 00:16:11,279
What's up with that? Look at this guy's keyboard. I want that keyboard. And a

220
00:16:08,480 --> 00:16:14,880
wireless microphone. What? He's even got the flip down mic on the side. Dude, it

221
00:16:13,360 --> 00:16:20,240
even has a YouTube logo in the background. That's wild. I don't like

222
00:16:16,720 --> 00:16:21,920
it. Okay, let's try doing a higher batch

223
00:16:20,240 --> 00:16:25,920
size though, cuz maybe when you know we're doing the same batch size, it's fine. But let's do let's go up to like

224
00:16:24,399 --> 00:16:30,639
16. Hold on. I want to see if there's a good one. This one's pretty good. That

225
00:16:28,720 --> 00:16:35,279
one's not bad. I could believe that there's a funky display that has like

226
00:16:33,680 --> 00:16:40,399
the power supply coming off the back like this or something like I His

227
00:16:37,040 --> 00:16:43,600
fingers are crossed weirdly. Yeah, he's

228
00:16:40,399 --> 00:16:45,120
missing one, I think. Yeah. But overall,

229
00:16:43,600 --> 00:16:48,720
if you just like threw this in the marketing collateral for something, not

230
00:16:46,720 --> 00:16:52,720
many people would notice right away. No. That's pretty wild. And this headset

231
00:16:50,240 --> 00:16:57,120
looks pretty sick. Yeah. The nice like pink purple. Yeah. I like it. Oh, he's

232
00:16:55,040 --> 00:17:02,720
missing a watch strap. Yeah, it's his skin. It's That's the new wearable. His

233
00:17:00,240 --> 00:17:06,480
finger is coming out of the computer and it's backwards. I don't know why the

234
00:17:04,079 --> 00:17:10,240
displays are backwards. I don't like it. I'm going to hit Okay, let's Your

235
00:17:08,480 --> 00:17:13,839
machine is still like really upset at you. Yeah, I think I I think I might

236
00:17:12,160 --> 00:17:17,520
just restart real quick. Did you hit run again or something? No, cuz your case

237
00:17:16,079 --> 00:17:21,679
sampler is still going. I bet you hit run again by accident.

238
00:17:19,919 --> 00:17:27,439
What' you do? I clicked it a few times. Oh my god. So, this is interesting

239
00:17:23,600 --> 00:17:29,840
though because I managed to output

240
00:17:27,439 --> 00:17:33,360
at the same time as you. Here we go. We've got Comfy UI with a stable

241
00:17:31,360 --> 00:17:36,720
diffusion checkpoint loaded up. Let's uh give it a simple prompt. YouTube host

242
00:17:35,280 --> 00:17:41,679
fixing a computer. Why don't we start with two in our batch size? Wait, wait,

243
00:17:39,679 --> 00:17:44,880
wait. Let's also put a couple of negative notes. I'm going to assume it's

244
00:17:43,679 --> 00:17:50,000
something you don't want. So, blonde hair. I'm going to say blonde. Blonde hair. Okay. No blonde hair. Okay. And

245
00:17:48,400 --> 00:17:54,880
we're just doing two. Yeah. Let's do two. Okay. And run. Only click it once.

246
00:17:52,720 --> 00:18:00,080
I only clicked it once. Dude, my memory is at 26 gigs. Mine started way before

247
00:17:58,160 --> 00:18:03,919
yours, too. Uh, yeah. Mine is Why is your memory

248
00:18:02,160 --> 00:18:07,840
usage so low? I don't know. We're getting about the same performance.

249
00:18:05,760 --> 00:18:11,440
Yeah. I'm going to check uh task manager instead of just GPUZ. Oh, wait. Yeah, it

250
00:18:09,840 --> 00:18:15,600
says 24 gigs now. Oh, it does. Okay, maybe it just had to spool up, I guess.

251
00:18:13,120 --> 00:18:19,760
Hey, how did we end up with the same dude? It totally is. Dude, mine is

252
00:18:18,080 --> 00:18:24,000
actually pretty convincing. I think yours is better. His we his fingers look

253
00:18:21,600 --> 00:18:27,679
wonky on the left hand. Yeah, they're like long. Um, but otherwise, it's like

254
00:18:26,320 --> 00:18:33,200
pretty convincing. It's a better mic than mine. This guy is psyched to have

255
00:18:29,919 --> 00:18:35,520
the world's skinniest display. I want

256
00:18:33,200 --> 00:18:38,640
that. What? It's like a tiny little bar. That's actually super cool. But we

257
00:18:37,520 --> 00:18:47,679
weren't expecting there to be a difference generating just two images. Let's increase our batch size to 16 cats

258
00:18:44,559 --> 00:18:49,600
destroying a supermarket. Black cats. No

259
00:18:47,679 --> 00:18:56,799
black cats. No black cats. Bad luck. I am using 42 gigs of VRAM. And you simply

260
00:18:53,600 --> 00:18:59,280
do not have 42 gigs of VRAM. So your

261
00:18:56,799 --> 00:19:02,720
system memory usage is way higher. Yeah. How much is yours? Oh yeah. You're

262
00:19:01,200 --> 00:19:06,480
barely using it. Yeah. That's like normal system usage um for what we're

263
00:19:05,200 --> 00:19:10,160
doing normally. Yeah. That's about 8 gig. It's all just running on the GPU,

264
00:19:08,640 --> 00:19:13,440
which is what you want. And you can actually see in the progress bar. Oh,

265
00:19:12,000 --> 00:19:17,120
yeah. You actually have progress. I don't even have a progress bar yet.

266
00:19:15,200 --> 00:19:21,200
Okay, I promise you I hit run. I'm not going to press it again. Yeah, it's

267
00:19:18,400 --> 00:19:26,480
still at like 23.5 gigs out of 24. And 3D is like fully busy. So, it's trying.

268
00:19:24,480 --> 00:19:31,120
It's just taking a hot minute. It can't. It's not even progressing yet. So

269
00:19:28,240 --> 00:19:36,640
imagine if you had like eight of these 48 gig 4090s set up in a giant like

270
00:19:34,640 --> 00:19:41,120
mining rig essentially. Yeah. And then was just like make me images of this

271
00:19:39,039 --> 00:19:45,919
stuff or generate a prompter. Write me write me stories so I can sell romance

272
00:19:43,440 --> 00:19:49,600
novels on Amazon and then generate the covers for them. Wow, look at my

273
00:19:47,520 --> 00:19:54,240
progress bar. There's like nothing. Yeah, you're getting crushed. Yours is

274
00:19:51,360 --> 00:19:58,000
like done already and I've got like 10% not even. To be clear, we're both

275
00:19:56,000 --> 00:20:01,520
running the same model. So, the actual quality of the output is going to be the

276
00:20:00,160 --> 00:20:04,880
same. Yeah, mine's just taking way longer. It's just the timing. Yeah, I

277
00:20:03,360 --> 00:20:10,240
can see why people are after these things, right? And with how little it

278
00:20:07,280 --> 00:20:13,520
actually costs to buy memory. Yes. Right. Like you can see on DM Exchange,

279
00:20:11,919 --> 00:20:20,240
we don't actually have spot pricing for DDDR 6X. Yeah. But DDDR6 is like what, a

280
00:20:17,919 --> 00:20:24,000
buck 80 per gigabyte or something? 290. 290 per gigabyte. So, even if it's

281
00:20:22,320 --> 00:20:28,320
double that, we're talking a few hundred bucks worth of additional memory when

282
00:20:26,160 --> 00:20:32,880
they remanufacture these cards. Yeah. Plus the PCD and power delivery and all

283
00:20:30,159 --> 00:20:35,280
that. I'm like stuck. Yours is going to finish and mine's

284
00:20:34,000 --> 00:20:40,000
going to be nowhere close. And the fact that this is so accessible that just like like you can literally just buy one

285
00:20:38,640 --> 00:20:43,280
of these and throw it in your computer. This didn't need it didn't need

286
00:20:41,760 --> 00:20:48,240
proprietary connections. It didn't have a special power specs. It's just a 450 W

287
00:20:45,840 --> 00:20:51,840
4090. I mean, just like mining, anyone can start like tooling around with AI.

288
00:20:50,320 --> 00:20:57,520
Yeah. You know what? Not just anyone can do though. What? Take their AI generated

289
00:20:55,200 --> 00:21:02,960
images and turn them into a real product. I am now teasing officially for

290
00:21:01,039 --> 00:21:07,679
the first time our leather jacket, which we're thinking

291
00:21:05,360 --> 00:21:11,679
we're going to call the Jensen. Matthew chucked this in an AI prompt. It

292
00:21:10,400 --> 00:21:17,440
was like, "Generate me a leather jacket." Dude, it is full of useless

293
00:21:14,880 --> 00:21:20,960
clips and buckles, pockets that aren't actually real. You may not have noticed

294
00:21:19,200 --> 00:21:26,000
this. two zippers. But there are actually two zippers in the front. We

295
00:21:24,000 --> 00:21:31,919
did have to make some tweaks to make it actually wearable. But this is as close

296
00:21:28,960 --> 00:21:35,679
to an AI generated jacket as you will actually be able to buy in person. You

297
00:21:34,480 --> 00:21:40,080
look like one of the anime characters that's got like six belts on. I know,

298
00:21:38,480 --> 00:21:43,440
right? Legitimately actually looks pretty cool. It looks pretty cool. It

299
00:21:41,679 --> 00:21:48,559
looks good. The only thing I would change is the dumb middles. No, no, no,

300
00:21:46,159 --> 00:21:54,320
no. It's a feature. See, look. You lose some weight.

301
00:21:51,440 --> 00:21:58,799
Suddenly it fits better. Boom. Slim fit. The Jensen coming soon to ltstore.com.

302
00:21:57,120 --> 00:22:04,720
Man, yours is done and mine is nowhere close. I don't think this one's finishing. But that definitely made cats

303
00:22:02,799 --> 00:22:08,720
destroying supermarket with no black cats. But what if you're not crazy about

304
00:22:06,400 --> 00:22:13,440
AI? In theory, cards like this with a ton of VRAM offer benefits in other

305
00:22:10,799 --> 00:22:18,640
workloads as well. So, why don't we see if it can outperform our regular 4090 in

306
00:22:16,000 --> 00:22:23,520
something like this massive Adobe Premiere project for how to build a PC,

307
00:22:21,039 --> 00:22:27,600
the last guide you'll ever need. As it turns out, even a huge featurelength

308
00:22:26,080 --> 00:22:32,320
project like this one with three terabytes of footage on the timeline,

309
00:22:29,679 --> 00:22:36,559
still only using about 16 gigs of VRAM. So, that's good news for me because it

310
00:22:34,799 --> 00:22:40,960
means I don't have to shell out for another dozen or so of these to chuck

311
00:22:38,480 --> 00:22:45,360
into our editing stations at the office. With that said, if you're working with a

312
00:22:42,720 --> 00:22:50,000
ton of layers, heavy VFX, or especially a lot of After Effects, it is possible

313
00:22:48,080 --> 00:22:54,080
that you could benefit from a card like this. What about Blender? What's the

314
00:22:52,320 --> 00:22:58,720
deal with this donut? It's really high poly. I asked a friend for a donut. Oh,

315
00:22:55,840 --> 00:23:02,720
okay. 2.1 gigs. Most files that you're going to get on Blender for free are

316
00:23:00,159 --> 00:23:04,799
like 300 megs at most. Oh, I see. So, we, you know, it was going to be really

317
00:23:03,679 --> 00:23:09,120
hard for us to actually max out the VRAM. Uh, but even with the 2.1 gig

318
00:23:06,799 --> 00:23:14,000
donut, copying it, multiplying it a bunch, we kind of the same on both

319
00:23:11,840 --> 00:23:18,480
systems. It might be a different story if we had like a bunch of shaders

320
00:23:15,520 --> 00:23:23,039
running and texture packs and stuff. Um, but at least just with polies, even in

321
00:23:21,120 --> 00:23:28,720
Blender, you're probably better off just doubling your actual system memory. Oh,

322
00:23:25,440 --> 00:23:30,559
that makes sense. Yeah. Okay, thanks.

323
00:23:28,720 --> 00:23:33,440
Finally, games. I guess we kind of spoiled this before, but I didn't

324
00:23:32,080 --> 00:23:37,039
actually get to play on it when we recorded those benchmarks, so I want to

325
00:23:35,200 --> 00:23:43,799
see how much VRAM this will actually use. Worst case scenario. Okay, frame

326
00:23:39,280 --> 00:23:43,799
gen rate tracing. Here we go.

327
00:23:45,440 --> 00:23:52,720
Maximum memory used about 14 14 12 gigs.

328
00:23:49,600 --> 00:23:55,200
So, in conclusion, benchmarks are like

329
00:23:52,720 --> 00:24:00,640
onions. Rather, they're like hips. They don't lie. So, don't buy one of these

330
00:23:57,360 --> 00:24:02,320
for gaming, but maybe consider one if

331
00:24:00,640 --> 00:24:06,960
you're looking for a bit of extra oomph in your productivity tasks that benefit

332
00:24:04,320 --> 00:24:10,799
from it or especially AI. I can't guarantee that it'll make a difference

333
00:24:08,320 --> 00:24:14,960
for every workload you have. And I can't even guarantee that it'll be reliable.

334
00:24:12,559 --> 00:24:20,559
Who knows? You know, these labbotomized 4090s that then get reassembled and

335
00:24:17,360 --> 00:24:22,720
shipped to you. Uh, good luck everybody.

336
00:24:20,559 --> 00:24:27,200
And good luck to our sponsor, Threat Locker. The best defense against cyber

337
00:24:25,200 --> 00:24:30,559
threats isn't always the latest and greatest security software. Although

338
00:24:28,960 --> 00:24:35,200
Threat Locker has that area covered, too. Sometimes a little extra knowledge

339
00:24:33,200 --> 00:24:39,840
goes a long way. That's why they're currently hosting a 100% free webinar

340
00:24:38,000 --> 00:24:43,600
series that is all about how to arm yourself with tips, tricks, and tools

341
00:24:42,159 --> 00:24:48,320
that will help secure your IT environment. Over 100 days, you will

342
00:24:45,919 --> 00:24:51,120
learn in depth about how to properly configure devices and cloud

343
00:24:49,679 --> 00:24:54,960
environments, how to strengthen application security, how to build a

344
00:24:52,960 --> 00:24:59,360
rapid and effective incident response plan, and so much more. Each session

345
00:24:57,440 --> 00:25:02,640
will give you practical step-by-step advice to help protect your business, no

346
00:25:01,200 --> 00:25:06,720
matter if you're inheriting an environment or starting one from

347
00:25:04,400 --> 00:25:11,039
scratch. So, don't wait. Sign up for free using our link in the description

348
00:25:08,480 --> 00:25:14,559
to catch up on any previous sessions and to make sure that you are enrolled for

349
00:25:12,720 --> 00:25:18,640
the next one. If you guys enjoyed this video, why not check out the time we

350
00:25:16,240 --> 00:25:22,799
showed how to work around NVIDIA's restrictions and game on one of their

351
00:25:20,960 --> 00:25:25,520
mining cards back in the day. That was pretty cool.