正在加载视频...

视频加载失败

返回首页

Who needs a 4090?

PowerGPU's profile picture

PowerGPU

392,449 subscribers

226,780 次观看 • 3 年前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

9 条评论

Shultsy 👾 的头像
Shultsy 👾3 年前

Assuming they are sitting there because no one wants to spend $1600 on a single part in a PC when you can build an entire PC for the price of that 4090 😂😂😂

PowerGPU 的头像
PowerGPU3 年前

@ShultsGaming We just got them in. Some are needed for some orders but we will have a few extra with this batch.

TheDFlawless 的头像
TheDFlawless3 年前

Lemme get one 😂

Above 的头像
Above3 年前

Hi yes hello 🙋🏻‍♂️

Ruqa🐺 的头像
Ruqa🐺3 年前

Would definetly help getting those extra frames while playing @VRChat 🥹

Street 🇭🇹 的头像
Street 🇭🇹3 年前

Not me, it’d blow up my system 🤣

Cheers Jeff 😎 的头像
Cheers Jeff 😎3 年前

Myself and @ChrisIsASaint12 and @hdz0603

Scott 🇺🇸🇬🇷 的头像
Scott 🇺🇸🇬🇷3 年前

I’ll take a free PC with whatever older spare parts you’ve got collecting dust. I ain’t even greedy. Thanks.

Moisty 的头像
Moisty3 年前

Yes please! 🙋‍♂️

相关视频

Who needs an RTX 4090 Strix?
1:43

Who needs an RTX 4090 Strix?

PowerGPU

123,545 次观看 • 3 年前

Intel 13900KS 1440p comp settings hitting 391FPS!! Gulag 300+FPS. Like/RT and I might give someone something who does. Intel i9 13900KS STOCK Gskill 7000mhz cl32 Asus TUF RTX 4090 STOCK Watch till the end 😂🤣
3:08

Intel 13900KS 1440p comp settings hitting 391FPS!! Gulag 300+FPS. Like/RT and I might give someone something who does. Intel i9 13900KS STOCK Gskill 7000mhz cl32 Asus TUF RTX 4090 STOCK Watch till the end 😂🤣

PowerGPU

119,350 次观看 • 3 年前

Who wants a brand new 4090?
0:38

Who wants a brand new 4090?

Doug "Censor" Martin

286,412 次观看 • 3 年前

We are proud to announce our AMD PowerSeries. ✅ Prime AMD 7700x/RTX 4070 Super $1999.99 ✅ Prestige 7800X3D/RTX 4080 Super $2999.99 ✅ Elite 7800X3D/RTX 4090 $4199.99
3:44

We are proud to announce our AMD PowerSeries. ✅ Prime AMD 7700x/RTX 4070 Super $1999.99 ✅ Prestige 7800X3D/RTX 4080 Super $2999.99 ✅ Elite 7800X3D/RTX 4090 $4199.99

PowerGPU

11,682 次观看 • 2 年前

Who has notifications on?
0:34

Who has notifications on?

PowerGPU

17,059 次观看 • 1 年前

Another Custom PC done. Who is next?
0:34

Another Custom PC done. Who is next?

PowerGPU

10,919 次观看 • 11 个月前

Who needs a boy?
1:07

Sensitive content

Who needs a boy?

Sofia ''Buff Girlfriend''

507,134 次观看 • 1 年前

Who needs a man?
1:13

Who needs a man?

Literally Heather

1,769,220 次观看 • 2 年前

Who needs a dragon
2:26

Who needs a dragon

IGBOCNN

232,510 次观看 • 1 个月前

Who needs a grinder
0:23

Who needs a grinder

Genius💡💹🧲 🤖

359,791 次观看 • 2 年前

who needs a grill?
1:00

who needs a grill?

Cooking Hub 🧑‍🍳

3,791,492 次观看 • 2 个月前

Who needs a road.
0:24

Who needs a road.

🔨Robert The Builder 🇺🇸

11,237 次观看 • 17 天前

Who needs a permit?
0:47

Who needs a permit?

Kevin Dalton

50,230 次观看 • 5 个月前

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

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

Yuchen Jin

234,951 次观看 • 1 年前

Who needs a Pack?! 🤷‍♂️
0:25

Sensitive content

Who needs a Pack?! 🤷‍♂️

DIESEL DISPENSARY

36,794 次观看 • 1 年前

WHO NEEDS A PC? 🤔
0:22

WHO NEEDS A PC? 🤔

Xidax PCs

25,904 次观看 • 1 年前

Who needs a good laugh?
0:57

Who needs a good laugh?

Constitutional Gator

259,092 次观看 • 2 年前