Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Building RTX 6000 PRO GPU Server #GPUServer #RTX6000 #TechInnovation #DataCenter #HighPerformance #ServerBuild #AIHardware #CloudComputing #InterServer #TechSolutions

InterServer

58,583 subscribers

67,721 views • 2 months ago •via X (Twitter)

#GPUServer #RTX6000 #TechInnovation #DataCenter #HighPerformance #ServerBuild #AIHardware #CloudComputing #InterServer #TechSolutions

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Take a peek inside our NYC data center! 🚀🔌 Check out the latest rack build-outs and see how InterServer is powering the city’s digital future. Innovation, connectivity, and infrastructure—watch it all come together! #DataCenter #NYC #InterServer #TechNews #CloudHosting

Take a peek inside our NYC data center! 🚀🔌 Check out the latest rack build-outs and see how InterServer is powering the city’s digital future. Innovation, connectivity, and infrastructure—watch it all come together! #DataCenter #NYC #InterServer #TechNews #CloudHosting

InterServer

33,200 views • 6 months ago

Interserver VPS Hosting

Interserver VPS Hosting

InterServer

116,240,525 views • 1 year ago

More Racks going online in 365 Datacenters.

More Racks going online in 365 Datacenters.

InterServer

31,051 views • 8 months ago

Playing with omnidreams ( inside flashdreams ( Fully interactive video generation at - 30FPS, - 720P resolution, - On a single RTX 6000 PRO GPU

Playing with omnidreams ( inside flashdreams ( Fully interactive video generation at - 30FPS, - 720P resolution, - On a single RTX 6000 PRO GPU

Ruilong Li

18,196 views • 2 months ago

768GB of VRAM. Eight RTX PRO 6000 Blackwell cards. Liquid-cooled. 4U. We reviewed the Comino Grando and it is the most capable version of this platform yet by a wide margin. Comino @NVIDIA #AI #GPU #server

768GB of VRAM. Eight RTX PRO 6000 Blackwell cards. Liquid-cooled. 4U. We reviewed the Comino Grando and it is the most capable version of this platform yet by a wide margin. Comino @NVIDIA #AI #GPU #server

StorageReview.com

46,879 views • 3 months ago

Four Intel Arc Pro B70s in one box: 32GB of GDDR6 each, 128GB total, about $4,000 in GPUs. In our testing the quad setup more than doubles the DGX Spark and only trails a single RTX Pro 6000 that is much more expensive. Full review on the site. #IntelArc #GPUs #AIHardware Intel

Four Intel Arc Pro B70s in one box: 32GB of GDDR6 each, 128GB total, about $4,000 in GPUs. In our testing the quad setup more than doubles the DGX Spark and only trails a single RTX Pro 6000 that is much more expensive. Full review on the site. #IntelArc #GPUs #AIHardware Intel

StorageReview.com

67,572 views • 1 month ago

Quick video on how we wire up new racks. Yellow cables are for the public network. Orange Cables are for the private network. Every cable is labeled with the corresponding port number.

Quick video on how we wire up new racks. Yellow cables are for the public network. Orange Cables are for the private network. Every cable is labeled with the corresponding port number.

InterServer

23,415 views • 9 months ago

GPU GIVEAWAY Buy a GPU × GTC 2026 = Give a GPU > RTX PRO 6000 Blackwell > 96GB VRAM • NVFP4 > ~$15K value > Brand new If this does well I’ll ask NVIDIA for more GPUs next time… maybe even DGX Sparks How to enter? Short clip here Full clip in the replies GO GO GO

Ahmad

36,697 views • 5 months ago

Finally got my hands on the big one. Qwen3.5-122B-A10B — 122 billion parameters. Too big for any single consumer GPU. So I rented 4 of each... and then one professional card to see if brute force even matters. - 1x RTX PRO 6000 (96GB): 101.4 tok/s - 4x 5090 (128GB): 87.0 tok/s - 4x 4090 (96GB): 25.1 tok/s - 4x 3090 (96GB): 20.8 tok/s One single $8,500 card beat four RTX 5090s

Finally got my hands on the big one. Qwen3.5-122B-A10B — 122 billion parameters. Too big for any single consumer GPU. So I rented 4 of each... and then one professional card to see if brute force even matters. - 1x RTX PRO 6000 (96GB): 101.4 tok/s - 4x 5090 (128GB): 87.0 tok/s - 4x 4090 (96GB): 25.1 tok/s - 4x 3090 (96GB): 20.8 tok/s One single $8,500 card beat four RTX 5090s

stevibe

195,832 views • 5 months ago

MiniMax M2.7 is 230B params. Can you actually run it at home? I tested Unsloth's UD-IQ3_XXS (80GB) on 4 different rigs: 🟠 4x RTX 4090 (96GB): 71.52 tok/s, TTFT 1045ms 🟢 4x RTX 5090 (128GB): 120.54 tok/s, TTFT 725ms 🟡 1x RTX PRO 6000 (96GB): 118.74 tok/s, TTFT 765ms 🟣 DGX Spark (128GB) — 24.41 tok/s, TTFT 741ms Backend: llama.cpp. Context: 32k. Max tokens: 4096. I went with IQ3_XXS because it's the biggest quant that fits in 96GB VRAM while still leaving safe headroom for 32k context. Same quant across all four rigs, fairest comparison I could run. Now look at rough peak GPU power draw: 🟠 4x4090 → 1,800W peak (450W × 4) 🟢 4x5090 → 2,300W peak (575W × 4) 🟡 RTX PRO 6000 → 600W peak 🟣 DGX Spark → 240W peak (whole system) The RTX PRO 6000 is the quiet winner. One card, 96GB, matching a 4x5090 rig at roughly a quarter of the power and zero multi-GPU headaches. Best tokens-per-watt by a wide margin. DGX Spark is slow on generation but pulls the least power of any rig here, around 240W for the whole system. Prefill-friendly, memory-rich, wall-socket-friendly. And yes, plenty of people cap their cards. Even then, 4x 4090 or 4x 5090 still pulls well over 1,200W from the GPUs alone.

MiniMax M2.7 is 230B params. Can you actually run it at home? I tested Unsloth's UD-IQ3_XXS (80GB) on 4 different rigs: 🟠 4x RTX 4090 (96GB): 71.52 tok/s, TTFT 1045ms 🟢 4x RTX 5090 (128GB): 120.54 tok/s, TTFT 725ms 🟡 1x RTX PRO 6000 (96GB): 118.74 tok/s, TTFT 765ms 🟣 DGX Spark (128GB) — 24.41 tok/s, TTFT 741ms Backend: llama.cpp. Context: 32k. Max tokens: 4096. I went with IQ3_XXS because it's the biggest quant that fits in 96GB VRAM while still leaving safe headroom for 32k context. Same quant across all four rigs, fairest comparison I could run. Now look at rough peak GPU power draw: 🟠 4x4090 → 1,800W peak (450W × 4) 🟢 4x5090 → 2,300W peak (575W × 4) 🟡 RTX PRO 6000 → 600W peak 🟣 DGX Spark → 240W peak (whole system) The RTX PRO 6000 is the quiet winner. One card, 96GB, matching a 4x5090 rig at roughly a quarter of the power and zero multi-GPU headaches. Best tokens-per-watt by a wide margin. DGX Spark is slow on generation but pulls the least power of any rig here, around 240W for the whole system. Prefill-friendly, memory-rich, wall-socket-friendly. And yes, plenty of people cap their cards. Even then, 4x 4090 or 4x 5090 still pulls well over 1,200W from the GPUs alone.

stevibe

191,782 views • 4 months ago

Building my friend his dream pc 👀🫣 using the MSI Gaming USA RTX 5090 LIGHTNING Z 😍😍⚡️⚡️ what do you think?? 👀👀 those decals be popping! PC Parts List: CPU: Intel Core Ultra 7 265KF Motherboard: MSI MEG Z890 GODLIKE GPU: MSI RTX 5090 Lightning Z RAM: Corsair Dominator Titanium DDR5 SSD: MSI Spatium M480 Pro 2TB Cooler: MSI CoreLiquid P1 360 PSU: MSI AI1600T PCIE5 (1600W) Case: MSI MEG Maestro 700L PZ

Building my friend his dream pc 👀🫣 using the MSI Gaming USA RTX 5090 LIGHTNING Z 😍😍⚡️⚡️ what do you think?? 👀👀 those decals be popping! PC Parts List: CPU: Intel Core Ultra 7 265KF Motherboard: MSI MEG Z890 GODLIKE GPU: MSI RTX 5090 Lightning Z RAM: Corsair Dominator Titanium DDR5 SSD: MSI Spatium M480 Pro 2TB Cooler: MSI CoreLiquid P1 360 PSU: MSI AI1600T PCIE5 (1600W) Case: MSI MEG Maestro 700L PZ

Nay.Tesseract

22,165 views • 5 months ago

FOUR 600W GPUS. 384GB OF GDDR7. AND DELL MADE THE INSTALL LOOK EASIER THAN BUILDING A GAMING PC. this is a Dell PowerEdge XE7740 receiving four NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. each card brings: 96GB GDDR7 ECC 24,064 CUDA cores 4 PFLOPS FP4 up to 600W but the most satisfying part is the cable management. every GPU power lead is already routed, labeled and held beside its assigned slot. drop in the card. lock the retention hardware. connect one 16-pin plug. no loose bundle hanging across the airflow path and no guessing which cable belongs where. the four-card build totals 384GB of GPU memory and 16 PFLOPS FP4. the 4U XE7740 supports up to eight of these GPUs, doubling that to 768GB and 32 PFLOPS FP4. honest line: the memory remains split between separate cards, and four GPUs can still pull up to 2.4kW. Dell made a rack-scale AI server this dense without turning the next GPU swap into cable surgery. bookmark & watch today ↓

FOUR 600W GPUS. 384GB OF GDDR7. AND DELL MADE THE INSTALL LOOK EASIER THAN BUILDING A GAMING PC. this is a Dell PowerEdge XE7740 receiving four NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. each card brings: 96GB GDDR7 ECC 24,064 CUDA cores 4 PFLOPS FP4 up to 600W but the most satisfying part is the cable management. every GPU power lead is already routed, labeled and held beside its assigned slot. drop in the card. lock the retention hardware. connect one 16-pin plug. no loose bundle hanging across the airflow path and no guessing which cable belongs where. the four-card build totals 384GB of GPU memory and 16 PFLOPS FP4. the 4U XE7740 supports up to eight of these GPUs, doubling that to 768GB and 32 PFLOPS FP4. honest line: the memory remains split between separate cards, and four GPUs can still pull up to 2.4kW. Dell made a rack-scale AI server this dense without turning the next GPU swap into cable surgery. bookmark & watch today ↓

Grimmer

26,693 views • 9 days ago

Jak ze stacji roboczej HP - Z6 zrobić środowisko do vibe codingu? Przepis jest prosty - stacja robocza z 1x GPU (akurat moja posiada 2x Nvidia RTX PRO 6000 Blackewell Max-Q), lokalna instalacja vllm'a albo SGLang, najnowszy model Qwen3-Coder-30B-A3B-Instruct i żegnajcie limity, ograniczenia, płatności. 100% lokalnie, bez przekazywania danych, bezpiecznie. Zobaczmy, czy dzięki takiej stacji kilka osób jest w stanie pracować lokalnie. Oczywiście opencode. #HP #ZbyHP #HPIncPolska #StacjeRoboczeHP [płatna współpraca]

Jak ze stacji roboczej HP - Z6 zrobić środowisko do vibe codingu? Przepis jest prosty - stacja robocza z 1x GPU (akurat moja posiada 2x Nvidia RTX PRO 6000 Blackewell Max-Q), lokalna instalacja vllm'a albo SGLang, najnowszy model Qwen3-Coder-30B-A3B-Instruct i żegnajcie limity, ograniczenia, płatności. 100% lokalnie, bez przekazywania danych, bezpiecznie. Zobaczmy, czy dzięki takiej stacji kilka osób jest w stanie pracować lokalnie. Oczywiście opencode. #HP #ZbyHP #HPIncPolska #StacjeRoboczeHP [płatna współpraca]

Remek Kinas

21,533 views • 5 months ago

watch gemma 4 12b q8 dancing on a single rtx 3090 at 33 tokens a second average. google dropped this two days ago and it's the kind of thing that quietly moves the floor. a fully multimodal model, text image and audio in one net, 256k context, apache licensed, running entirely on one consumer gpu, no one metering your tokens. what you're watching is the whole loop live: the server streaming tokens top left, the gpu pegged bottom left, the answer landing on the right. all local, all mine. a year ago this needed someone else's datacenter. today it's a card you can buy. open source isn't catching up anymore, it's setting the pace. how fast does yours run?

watch gemma 4 12b q8 dancing on a single rtx 3090 at 33 tokens a second average. google dropped this two days ago and it's the kind of thing that quietly moves the floor. a fully multimodal model, text image and audio in one net, 256k context, apache licensed, running entirely on one consumer gpu, no one metering your tokens. what you're watching is the whole loop live: the server streaming tokens top left, the gpu pegged bottom left, the answer landing on the right. all local, all mine. a year ago this needed someone else's datacenter. today it's a card you can buy. open source isn't catching up anymore, it's setting the pace. how fast does yours run?

Sudo su

36,614 views • 2 months ago

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

384GB of VRAM. On your desk. Not in a datacenter. Autonomous, the company behind SmartDesk, just open sourced complete build guides for a personal AI computer that runs open models on hardware no one can switch off. It's called Autonomous Computer. Three configurations, one philosophy: a model you rent can be cut off overnight. A model running in your own house can't. → Home build: 2x RTX 5090 workstation → Team build: 4x RTX PRO 6000 Blackwell, 384GB VRAM → On-prem business build: 8x RTX 4090/5090, up to 256GB VRAM Every config ships with the full bill of materials, 3D printable and CNC housing files, wiring diagrams, BIOS tuning, and assembly photos. Software side covers OS setup, NVIDIA drivers, and serving open models through Ollama, vLLM, and llama.cpp. Fork it. Change it. Build it. Sell it. MIT License. 100% Opensource. Repo:

Harman

47,898 views • 1 month ago

Timelapse #158 (12 hrs) - pushed myself super hard at the gym. Body hurts. - talked with George Hotz a little bit in the tinygrad discord server - Private contract work - Started a tinygrad bounty - Made some improvements to my local RL infra (rtx pro 6000 for inference/training and 3090 for the isolated compute to have the agents run kernels). Mainly on memory usage and moving away from cold loading as much as possible (SSDs are slow) so trying out vllm sleep mode

Timelapse #158 (12 hrs) - pushed myself super hard at the gym. Body hurts. - talked with George Hotz a little bit in the tinygrad discord server - Private contract work - Started a tinygrad bounty - Made some improvements to my local RL infra (rtx pro 6000 for inference/training and 3090 for the isolated compute to have the agents run kernels). Mainly on memory usage and moving away from cold loading as much as possible (SSDs are slow) so trying out vllm sleep mode

Elliot Arledge

18,468 views • 1 month ago

Serce nowej stacji Z8 Fury G5 - to, co najważniejsze dla tych, którzy zajmują się AI - GPU. To tam zrównoleglamy pracę. To tam ją akcelerujemy. Tak wygląda jedna karta Nvidia RTX PRO 6000 Blackwell Max-Q. Blackwell - więcej pamięci VRAM 96GB, chip GB202, 24064 core, pasmo 1.79 TB/s, co jest bardzo ważne w przypadku treningu i inferencji LLM'ów (cały czas to właśnie prędkość transferu pamięci jest ograniczeniem w tym zadaniu), FP16 (half) 110.1 TFLOPS, oczywiście sprzętowe wsparcie fp8 i fp4. #HP #ZbyHP #HPIncPolska #StacjeRoboczeHP [płatna współpraca]

Serce nowej stacji Z8 Fury G5 - to, co najważniejsze dla tych, którzy zajmują się AI - GPU. To tam zrównoleglamy pracę. To tam ją akcelerujemy. Tak wygląda jedna karta Nvidia RTX PRO 6000 Blackwell Max-Q. Blackwell - więcej pamięci VRAM 96GB, chip GB202, 24064 core, pasmo 1.79 TB/s, co jest bardzo ważne w przypadku treningu i inferencji LLM'ów (cały czas to właśnie prędkość transferu pamięci jest ograniczeniem w tym zadaniu), FP16 (half) 110.1 TFLOPS, oczywiście sprzętowe wsparcie fp8 i fp4. #HP #ZbyHP #HPIncPolska #StacjeRoboczeHP [płatna współpraca]

Remek Kinas

21,579 views • 11 months ago

Introducing PulseAI, where your data is your knowledge. PulseAI Platform is an agent-to-silicon AI infrastructure platform built to keep your data secure and sovereign, enabling the next AI enterprise. Offered in form factors for every stage of enterprise AI, PulseAI enables enterprise from initial pilot to hyperscale. Combining Gruve's AI-native services with NVIDIA-powered GPU architectures, it scales from 16 RTX 6000 PRO to 2,048 B300 GPUs, with security, storage, and compute integrated. The next enterprise is built on its own data and intelligence. We are here to enable it. Book your consultation: Read more on PulseAI from our Chief AI & Technology Officer Matt Robinson:

Introducing PulseAI, where your data is your knowledge. PulseAI Platform is an agent-to-silicon AI infrastructure platform built to keep your data secure and sovereign, enabling the next AI enterprise. Offered in form factors for every stage of enterprise AI, PulseAI enables enterprise from initial pilot to hyperscale. Combining Gruve's AI-native services with NVIDIA-powered GPU architectures, it scales from 16 RTX 6000 PRO to 2,048 B300 GPUs, with security, storage, and compute integrated. The next enterprise is built on its own data and intelligence. We are here to enable it. Book your consultation: Read more on PulseAI from our Chief AI & Technology Officer Matt Robinson:

Gruve

65,999 views • 2 months ago

timelapse #164 (15.5 hrs) - Burning midnight oil with the Kimi team benchmarking on kernels - Getting a Persistent Fused Mega Kernel for a Puffer Lib Environment (the full Craftax game) - Dipped for the night to have models run my overnight training runs on autopilot, including some kernel-based GRPO on qwen3.6 - private contract work - downloaded 1.1 TB of minecraft videos to train a foundation model on - optimized my minecraft foundation model training pipeline and kernels to train on 500k hrs of 128px at 10 fps in ~28 hrs on single gpu (5 hrs of learning per second on rtx pro 6000 blackwell) - doing it for the love of the game

timelapse #164 (15.5 hrs) - Burning midnight oil with the Kimi team benchmarking on kernels - Getting a Persistent Fused Mega Kernel for a Puffer Lib Environment (the full Craftax game) - Dipped for the night to have models run my overnight training runs on autopilot, including some kernel-based GRPO on qwen3.6 - private contract work - downloaded 1.1 TB of minecraft videos to train a foundation model on - optimized my minecraft foundation model training pipeline and kernels to train on 500k hrs of 128px at 10 fps in ~28 hrs on single gpu (5 hrs of learning per second on rtx pro 6000 blackwell) - doing it for the love of the game

Elliot Arledge

28,210 views • 1 month ago

Jolt Pro is a 100x improvement over existing zkVMs. After months of researching all existing zkVMs, we realized none of them could scale to what we needed with Zero. Then we came across Justin Thaler's work and Jolt, a research project from a16z crypto. We saw massive potential in the math and, finally, a viable way to scale to our needs. So we secretly assembled a team of some of the brightest minds across cryptography, GPU programming, and ASIC design to build an internal Jolt Pro team. Jolt Pro has no precompiles; it runs only RISC-V instructions, without introducing new ad hoc, error-prone constraints. It's impossible to compare against other zkVMs because they are not proving straight RISC-V, most of their work and speed gains exist in dangerous pre-compiles. Jolt Pro scales to infinity. The number of cells you can use in parallel is only limited by the size of the datacenter. Jolt Pro has a path to 4GHz cells using the same configuration we use for our 1.61 GHz cell today. By early 2027, it will be post-quantum and set the standard for all zkVMs. We will eventually make "zero-proofs", and others can try to beat our RISC-V proving in the open. For now, we stay heads down, building Zero to be everything the industry ever wanted. And then just a little more.

Jolt Pro is a 100x improvement over existing zkVMs. After months of researching all existing zkVMs, we realized none of them could scale to what we needed with Zero. Then we came across Justin Thaler's work and Jolt, a research project from a16z crypto. We saw massive potential in the math and, finally, a viable way to scale to our needs. So we secretly assembled a team of some of the brightest minds across cryptography, GPU programming, and ASIC design to build an internal Jolt Pro team. Jolt Pro has no precompiles; it runs only RISC-V instructions, without introducing new ad hoc, error-prone constraints. It's impossible to compare against other zkVMs because they are not proving straight RISC-V, most of their work and speed gains exist in dangerous pre-compiles. Jolt Pro scales to infinity. The number of cells you can use in parallel is only limited by the size of the datacenter. Jolt Pro has a path to 4GHz cells using the same configuration we use for our 1.61 GHz cell today. By early 2027, it will be post-quantum and set the standard for all zkVMs. We will eventually make "zero-proofs", and others can try to beat our RISC-V proving in the open. For now, we stay heads down, building Zero to be everything the industry ever wanted. And then just a little more.

LayerZero

29,409 views • 5 months ago