News
IndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value ChainIndustryTSMC’s grip on advanced chipmaking will face competitionIndustryCadence joins European Chip Design Platform to support semiconductor startups and SMEsMaking chipsMarc Hijink on ASML’s Culture, Supply Chain, and GeopoliticsProcessorsIntel's post-Nova Lake CPUs take shape as Razor Lake desktop and laptop variants surfaceAI chipsHow Google’s New AI Chip Software Helps It Battle NvidiaIndiaMore IC Packaging Plants Emerge In IndiaIndustryUS Tightens China AI Chip Access as Nvidia, TSMC and Semiconductor Stocks SlideDesignAxelera AI moves into HPC with TitaniaMaking chipsChinese envoy says chip equipment export curbs threaten EU-China trade thawIndiaSEMICON India 2026 Day 2 Sees 25 MoUs, Strategic Collaborations Across Semiconductor Value Chain
EveryChip
NVIDIA GeForce GTX TITAN / GeForce GTX 780 / GeForce GTX 770

GeForce 700 series

Nvidia graphics card series from 2013 using Kepler and Maxwell chips

Photo: Hyins, Public domain, via Wikimedia Commons

The GeForce 700 series is a line of graphics processing units released by Nvidia starting in February 2013. It primarily uses the Kepler microarchitecture, with some entry models based on Fermi and later high-end cards introducing Maxwell. The series includes desktop and mobile variants for gaming and computational tasks.

Share on WhatsApp

  • Launched in February 2013 with the GeForce GTX Titan
  • Uses Kepler, Maxwell, and Fermi microarchitectures
  • GK110 chip contains up to 7.08 billion transistors
  • Introduced Hyper-Q with 32 hardware work queues
  • Manufactured by TSMC on 28 nm and 40 nm processes

What it is

The GeForce 700 series comprises graphics processing units developed by Nvidia for desktop and mobile computers. First launched in February 2013 with the GTX Titan, the family serves gamers and professionals requiring visual rendering or parallel computation. Most chips rely on the Kepler architecture, though early entries use older Fermi designs and later models adopt Maxwell. Manufactured by TSMC, these GPUs support modern display standards and offer varying levels of performance across entry-level to enthusiast tiers.

How it came about

Nvidia introduced the series in early 2013, beginning with the high-performance GTX Titan on February 19. The GTX 780 followed in May, targeting the upper end of the market. Mobile versions arrived in April of that year. The lineup was positioned as a refresh of the previous generation, integrating improved computational features while maintaining compatibility with existing software ecosystems. It succeeded the GeForce 600 series and preceded the 900 series.

Inside the chip

The architecture focuses on parallel task execution to boost energy efficiency. The GK110 chip, central to the high-end models, features up to 64 double-precision cores per streaming multiprocessor, a significant increase over prior designs. It introduces Hyper-Q, which expands hardware work queues from one to thirty-two, allowing better utilization of processing units. Dynamic parallelism enables kernels to launch other kernels directly on the GPU, reducing CPU overhead. Register file space and L2 cache capacity were also expanded to improve data handling.

How it was made

TSMC manufactured the chips using 28 nm and 40 nm process nodes. The flagship GK110 die contains approximately 7.08 billion transistors. Smaller variants like the GK104 hold 3.54 billion, while entry-level Fermi-based chips such as the GF119 have 292 million. The production leverages standard semiconductor fabrication techniques to balance performance and power consumption across the different tiers of the product stack.

GeForce 700 series
A drawing made by EveryChip from what this page says. It is a diagram, not a picture of the real chip.

Where it went

These GPUs power desktop PCs and laptops for gaming, professional visualization, and high-performance computing. They support DirectX 12 feature level 11_0, OpenGL 4.6, and Vulkan APIs. Features like NVENC provide hardware-accelerated video encoding, while PureVideo handles decoding. The cards can drive multiple high-resolution displays, including 4K output via HDMI 1.4a and DisplayPort 1.2, making them suitable for multi-monitor setups and media consumption.

Versions and family

The series includes entry-level GT models, mid-range GTX cards, and enthusiast-grade Titan variants. Codenames include GK110, GK208, GM107, and GM108. The mobile 700M series shares similar specifications but is optimized for laptops. Some desktop models like the GTX 750 and 750 Ti use the newer Maxwell architecture, distinguishing them from the Kepler-based majority. The Titan Z represents a dual-GPU configuration within the lineup.

Why it matters

The introduction of Hyper-Q and dynamic parallelism marked a shift toward more efficient compute workloads on consumer hardware. By increasing double-precision throughput, the GK110 bridged the gap between gaming GPUs and professional accelerators. The series maintained strong driver support for several years, with security updates for Maxwell models scheduled until late 2028, ensuring long-term usability for legacy systems.

Problems and reception

Driver support for older operating systems like Windows XP ended with specific legacy branches. Nvidia transitioned Kepler desktop GPUs to legacy status in 2021, providing security patches until 2024. Game Ready Driver support for Maxwell-based models ceased in December 2025, though critical security updates continue. Some users experienced issues with CUDA support on newer drivers for Kepler chips in Windows 7 and 8.1 environments.

Questions people ask about GeForce 700 series

What microarchitectures are used in the GeForce 700 series?

The series primarily uses the Kepler microarchitecture. Some entry-level cards are based on the older Fermi design, while later models, such as the GTX 750, utilize the Maxwell architecture. This mix allows Nvidia to cover various performance segments.

Who manufactures the GeForce 700 series chips?

Taiwan Semiconductor Manufacturing Company (TSMC) produces the GPUs. They use both 28 nm and 40 nm process technologies depending on the specific chip model, such as the GK110 or the older GF119.

Does the GeForce 700 series support DirectX 12?

Yes, all cards in the series support DirectX 12.0, but they operate at feature level 11_0. This means they can run DX12 applications but do not support all the advanced features found in newer hardware generations.

What is Hyper-Q in the context of these GPUs?

Hyper-Q is a feature in the GK110 chip that increases hardware work queues from one to thirty-two. This allows the GPU to handle multiple task streams simultaneously, improving utilization and performance for parallel computing workloads.

Good reading and sources

Where this page comes from

The facts on this page come from the Wikipedia article "GeForce 700 series", written by its contributors and used under the CC BY-SA 4.0 licence, and from its Wikidata record (CC0). EveryChip rewrote the text in its own words, with AI assistance, and compares every page with the article to make sure no passage is copied. It may be reused under the same CC BY-SA 4.0 licence with a link back.

It may contain mistakes, and figures change over time. Nothing here is investment or buying advice. If something is wrong, tell us. Last refreshed 2026-11-14.

Photo credits on this page

The small pictures above come from Wikimedia Commons under free licences. Some are cropped to fit.

The weekly digest

Every Monday: the chip of the day, new pages on EveryChip, and the conferences and anniversaries of the week ahead.