Yotta NM1 Navi Mumbai
- Uptime Institute Tier IV certified
- Dual utility feeds from separate substations
Blackwell · PCIe Server Edition
RTX PRO 6000 Blackwell servers, bought and hosted in India.
RTX PRO 6000 Blackwell Server Edition doubles the L40S’s memory to 96 GB per card, enough to serve many 70B-class models on a single PCIe server.
- GPU memory
- 96 GB GDDR7 per GPU
- GPU power
- Up to 600 W per GPU (configurable lower)
- Server power
- Up to 4.8 kW of GPU power for 8 cards, plus CPUs and fans
- Rack space · cooling
- Typically 4U · Air
Shipping Lead time, October 2026: Quoted per order · All GPU lead times
Good fit for
Who buys RTX PRO 6000 Blackwell.
- Inference with large memory per card
- Rendering, simulation and digital twins
- Teams outgrowing L40S
The hardware
What an RTX PRO 6000 Blackwell server looks like.
4U server with 4–8 PCIe cards. 96 GB GDDR7 per GPU, up to 600 W per GPU (configurable lower), typically 4u of rack space.
- Server power: Up to 4.8 kW of GPU power for 8 cards, plus CPUs and fans
- Cooling: Air
Hosting
Where an RTX PRO 6000 Blackwell server runs.
At up to 600 W a card, an eight-card server draws far more than an L40S system. We place it against its full rated draw, or a power-capped configuration if you choose one.
How managed hosting worksYotta D1 Greater Noida
- Dual 220 kV feeds with an on-site substation
- 48 hours of on-site backup power
RTX PRO 6000 Blackwell questions
RTX PRO 6000 or L40S?
RTX PRO 6000 has twice the memory and newer architecture; L40S costs less and draws less power. Memory needs usually decide it.
Can the power draw be reduced?
Yes. The Server Edition can be configured to lower power limits, trading some performance for density.
Is this the same as the workstation card?
No. The Server Edition is passively cooled for rack servers. Workstation cards are built for desktop chassis.
Other GPU servers
H200141 GB HBM3e per GPU · Up to ~10.2 kW per serverH10080 GB HBM3 per GPU · Up to ~10.2 kW per serverB200180 GB HBM3e per GPU · Up to ~14.3 kW per serverB300288 GB HBM3e per GPU · Up to ~14 kW per serverGB300 NVL7220 TB HBM3e across 72 GPUs · ~132–140 kW per rackL40S48 GB GDDR6 per GPU · 2.8 kW of GPU power for 8 cards, plus CPUs and fansAMD MI300X192 GB HBM3 per GPU · 6 kW of GPU power for 8 GPUs, plus CPUs and fans
Owning one
Managed GPU hosting
Rack, power, cooling, network and remote hands for servers you own.
Learn more →Finance the purchase
Lender-ready quotes and asset records for your bank or NBFC.
Learn more →
Power and cooling guide
kW, amps and tons of cooling for every GPU class.
Learn more →
Sell or swap
Tested, valued and sold, or traded up for newer GPUs.
Learn more →