ZWZixi Wang
Notes

Note / GPU

The NVIDIA GPU Product Lineage

A map from Fermi to Rubin that separates consumer, professional, and data-center GPUs from NVIDIA's system-level products.

NVIDIA names are easy to confuse because GPU architectures, board products, market brands, modules, superchips, and rack-scale systems often appear in the same conversation. This guide separates discrete GPUs, embedded SoCs and modules, CPU-GPU superchips, and server or rack systems.

The main chronology follows one strict rule: products share a row only when they use the same GPU architecture.

1. Start with the naming layers

LayerTypical namesIntended use
Consumer GPU brandGeForce, GeForce GTX, GeForce RTXGaming, personal creation, and personal AI computing
Flagship consumer / developer sub-lineTITANAn ultra-high-end line from 2013-2018; part of its market position later moved to GeForce RTX 90-class products
Professional GPU brandQuadro, Quadro RTX, RTX A, RTX Ada, RTX PROCAD, DCC, professional visualization, enterprise AI, and workstations
Data-center GPU brandTesla, A series, H series, B series, Rubin GPUAI training, inference, HPC, and data-center acceleration

RTX is not a single brand at the same level as GeForce, Quadro, or Tesla. GeForce RTX is a consumer line. Quadro RTX, RTX A, RTX Ada, and RTX PRO are professional lines.

2. Discrete GPU evolution since 2010

This table contains only discrete GPU or accelerator-card products. GH200, GB200, GB300, NVL72, DGX, TITAN, and similar system or superchip names are intentionally excluded.

Years / architectureConsumer GeForceProfessional Quadro / NVIDIA RTXTesla / Data Center GPU
2010-2011 · FermiGeForce GTX 480
GeForce GTX 580
Quadro 4000
Quadro 5000
Quadro 6000
Tesla C2050
Tesla C2070
Tesla M2090
2012-2014 · KeplerGeForce GTX 680
GeForce GTX 780 Ti
Quadro K5000
Quadro K6000
Tesla K10
Tesla K20
Tesla K40
2014-2016 · MaxwellGeForce GTX 980
GeForce GTX 980 Ti
Quadro M4000
Quadro M5000
Quadro M6000
Tesla M4
Tesla M40
Tesla M60
2016-2017 · PascalGeForce GTX 1080
GeForce GTX 1080 Ti
Quadro P5000
Quadro P6000
Tesla P4
Tesla P40
Tesla P100
2017-2018 · Volta-Quadro GV100Tesla V100
2018-2020 · TuringGeForce RTX 2060
GeForce RTX 2080 Ti
Quadro RTX 4000
Quadro RTX 5000
Quadro RTX 6000
Quadro RTX 8000
NVIDIA Tesla T4
2020-2022 · AmpereGeForce RTX 3060
GeForce RTX 3080
GeForce RTX 3090
GeForce RTX 3090 Ti
NVIDIA RTX A2000
RTX A4000
RTX A4500
RTX A5000
RTX A5500
RTX A6000
NVIDIA A2
A10
A16
A30
A40
A100
2022-2024 · Hopper--NVIDIA H100
NVIDIA H200
2022-2024 · Ada LovelaceGeForce RTX 4060
GeForce RTX 4070
GeForce RTX 4080
GeForce RTX 4090
NVIDIA RTX 2000 Ada
RTX 4000 Ada
RTX 4500 Ada
RTX 5000 Ada
RTX 6000 Ada
NVIDIA L4
L40
L40S
2024-2025 · Blackwell--NVIDIA B100
NVIDIA B200
2025-2026 · BlackwellGeForce RTX 5050
GeForce RTX 5060
GeForce RTX 5060 Ti
GeForce RTX 5070
GeForce RTX 5070 Ti
GeForce RTX 5080
GeForce RTX 5090
NVIDIA RTX PRO 2000 Blackwell
RTX PRO 4000 Blackwell
RTX PRO 4500 Blackwell
RTX PRO 5000 Blackwell
RTX PRO 6000 Blackwell Workstation Edition
RTX PRO 6000 Blackwell Max-Q Workstation Edition
RTX PRO 6000 Blackwell Server Edition
2025-2026 · Blackwell Ultra--NVIDIA B300
2026 · Rubin--NVIDIA Rubin GPU
NVIDIA Rubin CPX

3. The shortest useful family tree

Early graphics
NV1 -> RIVA
        |
        |- GeForce -> GTX -> GeForce RTX -> RTX 90 class
        |             \- TITAN --------------------^
        |
        |- Quadro -> Quadro RTX -> RTX A -> RTX Ada -> RTX PRO
        |
        \- CUDA -> Tesla -> A100 -> H100/H200 -> B100/B200
                                                  -> B300 -> Rubin GPU

Mobile and embedded
Tegra -> Jetson / DRIVE / SHIELD

Cloud and virtualization
GRID -> NVIDIA vGPU -> RTX Virtual Workstation

AI systems (a parallel system layer, not a GPU generation)
Data Center GPU --combined into--> DGX / HGX / MGX / NVL

Data-center networking
Mellanox -> ConnectX / BlueField / Spectrum-X / Quantum

4. Ampere-and-newer PCIe GPUs for AI training

This table includes major NVIDIA products that use a standard PCIe x16 add-in-card form factor, have strictly more than 16 GB of memory per GPU, support CUDA and Tensor Cores, and can be used for AI training or fine-tuning.

The compute column uses theoretical FP32 peak throughput as a consistent cross-line reference. Real training performance also depends on BF16, FP16, TF32, and FP8 Tensor Core throughput, memory bandwidth, software support, and workload shape.

ProductMemoryFP32 peakPCIe
GeForce RTX 309024GB GDDR6X≈35.6 TFLOPSPCIe 4.0 x16
GeForce RTX 3090 Ti24GB GDDR6X≈40.0 TFLOPSPCIe 4.0 x16
NVIDIA RTX A450020GB GDDR6 ECC23.7 TFLOPSPCIe 4.0 x16
NVIDIA RTX A500024GB GDDR6 ECC27.8 TFLOPSPCIe 4.0 x16
NVIDIA RTX A550024GB GDDR6 ECC34.1 TFLOPSPCIe 4.0 x16
NVIDIA RTX A600048GB GDDR6 ECC38.7 TFLOPSPCIe 4.0 x16
NVIDIA A1024GB GDDR631.2 TFLOPSPCIe 4.0 x16
NVIDIA A3024GB HBM210.3 TFLOPSPCIe 4.0 x16
NVIDIA A4048GB GDDR6 ECC37.4 TFLOPSPCIe 4.0 x16
NVIDIA A100 PCIe40GB HBM219.5 TFLOPSPCIe 4.0 x16
NVIDIA A100 80GB PCIe80GB HBM2e19.5 TFLOPSPCIe 4.0 x16
GeForce RTX 409024GB GDDR6X83.0 TFLOPSPCIe 4.0 x16
NVIDIA RTX 4000 SFF Ada Generation20GB GDDR6 ECC19.2 TFLOPSPCIe 4.0 x16
NVIDIA RTX 4000 Ada Generation20GB GDDR6 ECC26.7 TFLOPSPCIe 4.0 x16
NVIDIA RTX 4500 Ada Generation24GB GDDR6 ECC39.6 TFLOPSPCIe 4.0 x16
NVIDIA RTX 5000 Ada Generation32GB GDDR6 ECC65.3 TFLOPSPCIe 4.0 x16
NVIDIA RTX 6000 Ada Generation48GB GDDR6 ECC91.1 TFLOPSPCIe 4.0 x16
NVIDIA L424GB GDDR630.3 TFLOPSPCIe 4.0 x16
NVIDIA L4048GB GDDR6 ECC≈90.5 TFLOPSPCIe 4.0 x16
NVIDIA L40S48GB GDDR6 ECC91.6 TFLOPSPCIe 4.0 x16
NVIDIA H100 PCIe80GB HBM2e51.0 TFLOPSPCIe 5.0 x16
NVIDIA H100 NVL94GB HBM360.0 TFLOPSPCIe 5.0 x16
NVIDIA H200 NVL141GB HBM3e60.0 TFLOPSPCIe 5.0 x16
GeForce RTX 509032GB GDDR7≈104.9 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 4000 Blackwell SFF Edition24GB GDDR7 ECC24.0 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 4000 Blackwell24GB GDDR7 ECC40.0 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 4500 Blackwell Server Edition32GB GDDR7 ECC51.0 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 5000 Blackwell48GB GDDR7 ECC70.0 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 5000 72GB Blackwell72GB GDDR7 ECC70.0 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition96GB GDDR7 ECC110 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 6000 Blackwell Workstation Edition96GB GDDR7 ECC125 TFLOPSPCIe 5.0 x16
NVIDIA RTX PRO 6000 Blackwell Server Edition96GB GDDR7 ECC120 TFLOPSPCIe 5.0 x16

How to read the list

Architecture, brand, board form factor, and system product answer different questions:

  • the architecture identifies a generation of GPU design;
  • the product line defines a market, driver, certification, and support boundary;
  • the board form factor determines host compatibility, power, cooling, and interconnect constraints;
  • a system product combines GPUs with CPUs, interconnects, and networking into a node or rack.

FP32 peak throughput is only a common comparison point. For training and inference, memory capacity, memory bandwidth, low-precision Tensor Core throughput, interconnect, power, and software support often determine practical performance more directly.