RTX 50 Series
GeForce RTX 5090
CUDA21 760
Memory32 GB GDDR7
Bus512-bit
TGP575 W
Flagship card for 4K, AI PCs, local models and heavy creator workflows.
GeForce RTX 40 / RTX 50
NVIDIA GeForce RTX graphics cards
A sourcing page for GeForce RTX requests: B2B procurement, system integrators, AI PCs, creator builds and entry workstation projects. The cards show NVIDIA reference data; final offers are verified against the exact ASUS, Gigabyte, MSI, PNY or other vendor SKU.
Related sections
NVIDIA catalog navigation
For mixed requests such as GPU + ConnectX + cables, use the common RFQ and attach the BOM.
NVIDIA GeForce RTX graphics cards
B2B sourcing of NVIDIA GeForce RTX 40 and RTX 50 graphics cards: RTX 5090, 5080, 5070 Ti, 5070, 5060 Ti, 5060, 5050, RTX 4090, 4080 Super, 4070 Ti Super, 4070 Super, 4070, 4060 Ti and 4060. We verify SKU, vendor, dimensions, power and warranty route.
Open sectionNVIDIA RTX professional workstation GPUs
B2B sourcing of NVIDIA RTX PRO and RTX Ada workstation GPUs: RTX PRO 6000 Blackwell, RTX 6000 Ada, RTX 5000 Ada, RTX 4500 Ada and RTX 4000 Ada. We verify ECC, DisplayPort, form factor and certifications.
Open sectionNVIDIA Networking equipment
B2B sourcing of NVIDIA Networking products: Quantum InfiniBand, Spectrum Ethernet, ConnectX adapters, BlueField DPU and LinkX cables. We verify ports, speed, latency, firmware and datasheets.
Open sectionNVIDIA data center GPU accelerators
B2B sourcing of NVIDIA data center GPUs: L40S, L4, H100 NVL, H100, H200 and B200. We verify form factor, cooling, power, TFLOPS, server compatibility and datasheets.
Open sectionNVIDIA Jetson for robotics and Edge AI
B2B sourcing of NVIDIA Jetson modules and developer kits: Jetson AGX Thor, AGX Orin, Orin NX and Orin Nano. We verify TOPS, power, dimensions, camera interfaces, I/O and JetPack.
Open sectionCatalog
Product and specification cards
Cards do not replace datasheets; they help structure the initial procurement request and identify what must be verified.
RTX 50 Series
GeForce RTX 5080
CUDA10 752
Memory16 GB GDDR7
Bus256-bit
TGP360 W
High-end RTX 50 card for gaming and creator builds where DLSS 4 and GDDR7 matter.
RTX 50 Series
GeForce RTX 5070 Ti
CUDA8 960
Memory16 GB GDDR7
Bus256-bit
TGP300 W
Strong 1440p and creator segment, often practical for batch sourcing.
RTX 50 Series
GeForce RTX 5070
CUDA6 144
Memory12 GB GDDR7
Bus192-bit
TGP250 W
Baseline RTX 50 option for mass gaming configurations and AI PCs.
RTX 50 Series
GeForce RTX 5060 Ti
CUDA4 608
Memory16 / 8 GB GDDR7
Bus128-bit
TGP180 W
Practical 1080p and 1440p segment for system builds.
RTX 50 Series
GeForce RTX 5060
CUDA3 840
Memory8 GB GDDR7
Bus128-bit
TGP145 W
Mass-market RTX card for budget-conscious configurations.
RTX 50 Series
GeForce RTX 5050
CUDA2 560
Memory8 GB GDDR6
Bus128-bit
TGP130 W
Entry RTX 50 card for budget-conscious batches where DLSS 4, low power and price matter.
RTX 40 Series
GeForce RTX 4090
CUDA16 384
Memory24 GB GDDR6X
Bus384-bit
TGP450 W
Availability and alternatives should be verified carefully because the RTX 4090 market is region dependent.
RTX 40 Series
GeForce RTX 4080 SUPER
CUDA10 240
Memory16 GB GDDR6X
Bus256-bit
TGP320 W
Sourcing option for high-performance gaming and creator configurations.
RTX 40 Series
GeForce RTX 4070 Ti SUPER
CUDA8 448
Memory16 GB GDDR6X
Bus256-bit
TGP285 W
Balanced 1440p and light 4K card with frequent price/performance demand.
RTX 40 Series
GeForce RTX 4070 SUPER
CUDA7 168
Memory12 GB GDDR6X
Bus192-bit
TGP220 W
Mainstream RTX 40 card for 1440p, creator scenarios and sourcing where price, availability and warranty region matter.
RTX 40 Series
GeForce RTX 4070
CUDA5 888
Memory12 GB GDDR6 / GDDR6X
Bus192-bit
TGP200 W
Base RTX 4070 option for stable commercial builds where broad AIB SKU availability matters.
RTX 40 Series
GeForce RTX 4060 Ti
CUDA4 352
Memory16 / 8 GB GDDR6
Bus128-bit
TGP160 / 165 W
Entry RTX segment for 1080p/1440p where the 8 GB or 16 GB memory version must be confirmed before quoting.
RTX 40 Series
GeForce RTX 4060
CUDA3 072
Memory8 GB GDDR6
Bus128-bit
TGP115 W
Most accessible RTX 40 card for mass builds, office AI PCs and tightly budgeted batches.
What we verify before pricing
- NVIDIA publishes reference or Founders Edition data. For AIB cards we verify length, thickness, weight, power connectors, OC clocks and warranty region.
- For a commercial quote, send the exact model, quantity, destination country, acceptable vendors, packaging and warranty requirements.
What to send
Model, SKU, quantity, acceptable brands, delivery country, warranty, compatibility, timeline and document requirements. For networking and data center projects, attach the BOM early.
Specification sources
Parameters are checked against official NVIDIA pages and datasheets. For AIB/OEM models, final dimensions, clocks, weight and part number are confirmed with the vendor.
RFQ
Send an NVIDIA request
Attach a model list or BOM for a faster response. If you do not have an exact SKU, describe the use case: gaming, workstation, AI server, networking fabric or Jetson prototype.