NVIDIA GeForce GTX 970
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA GeForce GTX 970 Specifications
GeForce GTX 970 GPU Core
Shader units and compute resources
The NVIDIA GeForce GTX 970 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
GTX 970 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the GeForce GTX 970's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The GeForce GTX 970 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's GeForce GTX 970 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce GTX 970's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
GeForce GTX 970 by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the GTX 970, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
GTX 970 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce GTX 970 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Maxwell 2.0 Architecture & Process
Manufacturing and design details
The NVIDIA GeForce GTX 970 is built on NVIDIA's Maxwell 2.0 architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the GTX 970 will perform in GPU benchmarks compared to previous generations.
NVIDIA's GeForce GTX 970 Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA GeForce GTX 970 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the GeForce GTX 970 to maintain boost clocks without throttling.
GeForce GTX 970 by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA GeForce GTX 970 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA GeForce GTX 970. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
GeForce GTX 970 Product Information
Release and pricing details
The NVIDIA GeForce GTX 970 is manufactured by NVIDIA as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the GeForce GTX 970 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
GeForce GTX 970 Benchmark Scores
3dmark_3dmark_steel_nomad_dx12Source
3DMark Steel Nomad is the latest GPU benchmark running at native 4K with DirectX 12. It's roughly 3x more demanding than Time Spy, testing NVIDIA GeForce GTX 970 with cutting-edge rendering techniques. The benchmark uses state-of-the-art graphics technologies to stress modern hardware. Scores accurately predict NVIDIA GeForce GTX 970 performance in demanding AAA games at 4K resolution.
geekbench_metalSource
Geekbench Metal tests GPU compute using Apple's Metal API. This shows how NVIDIA GeForce GTX 970 performs in macOS and iOS applications that leverage GPU acceleration.
geekbench_openclSource
Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how NVIDIA GeForce GTX 970 handles parallel computing tasks like video encoding and scientific simulations. OpenCL is widely supported across different GPU vendors and platforms. Higher scores benefit applications that leverage GPU acceleration for non-graphics workloads.
geekbench_vulkanSource
Geekbench Vulkan tests GPU compute using the modern low-overhead Vulkan API. This shows how NVIDIA GeForce GTX 970 performs with next-generation graphics and compute workloads.
passmark_directx_10Source
DirectX 10 tests NVIDIA GeForce GTX 970 with the graphics API introduced with Windows Vista. This shows performance in games from the 2007-2009 era that targeted this feature level. DX10 introduced geometry shaders and other features still used today.
passmark_directx_11Source
DirectX 11 tests NVIDIA GeForce GTX 970 with the widely-used graphics API powering most current games. This shows mainstream gaming performance across the majority of today's titles. DX11 remains the most common rendering path even in newer games. Tessellation and compute shaders introduced in DX11 are heavily used in modern game engines.
passmark_directx_12Source
DirectX 12 tests NVIDIA GeForce GTX 970 with the modern low-overhead graphics API. This shows performance in next-gen games that leverage DX12 features like ray tracing and mesh shaders.
passmark_directx_9Source
DirectX 9 tests NVIDIA GeForce GTX 970 performance with the legacy graphics API still used by older games. This shows compatibility and performance with classic titles from the 2000s era.
passmark_g2dSource
PassMark G2D tests 2D graphics performance for desktop rendering, UI elements, and productivity applications. This shows how NVIDIA GeForce GTX 970 handles everyday visual tasks.
passmark_g3dSource
PassMark G3D measures overall 3D graphics performance of NVIDIA GeForce GTX 970 across DirectX 9 through 12 tests. This provides a comprehensive gaming capability score. The combined result predicts performance across various game engines and API versions.
passmark_gpu_computeSource
GPU compute tests parallel processing capability of NVIDIA GeForce GTX 970 using OpenCL. This shows performance in video encoding, scientific computing, and AI workloads.
About NVIDIA GeForce GTX 970
The NVIDIA GeForce GTX 970, built on the Maxwell 2.0 architecture with the GM204 chip, remains a notable entry in the GeForce 900 generation. Produced on a 28 nm process at TSMC, this end-of-life card houses 5,200 million transistors on a 398 mm² die. With a launch MSRP of 329 USD, its benchmark data reveals a product that, while dated, still holds specific utility for legacy systems and 1080p gaming.
Benchmark Performance
The GTX 970’s average benchmark score of 8024 places it at the 40th percentile of all GPUs, indicating a mid-to-low-tier standing in the current landscape. Its synthetic performance is highly variable across APIs. In Geekbench compute tests, the card shows relative strength, scoring 31001 in Vulkan and 28528 in OpenCL, with a Metal score of 13595. However, PassMark results paint a different picture of legacy API performance, with a DirectX 11 score of 71, a DirectX 9 score of 143, and significantly lower scores of 46 for DirectX 10 and 41 for DirectX 12.
The 3DMark Steel Nomad DX12 test yields a score of 369, which is a modern, demanding workload where the card clearly struggles. The disparity between its Geekbench compute scores and its low PassMark DX12 score suggests that while the raw compute hardware is functional, driver optimization and architectural support for newer APIs are lacking. The PassMark G3D score of 9638 and G2D score of 764 provide a general baseline, but the compute score of 4073 confirms the card is not designed for heavy parallel workloads.
The data shows that the GTX 970 is virtually tied with its closest rivals in aggregate performance. It is a mere 0.1% ahead of the NVIDIA GeForce GTX 650 Ti and 0.2% ahead of the AMD Radeon R9 M360. Conversely, it trails the NVIDIA GRID K2 by 0.6% and the NVIDIA GeForce GTX 675MX by 0.9%. These sub-1% deltas are negligible, meaning that in average synthetic benchmarks, the GTX 970 offers no meaningful performance advantage over these older or lower-tier competitors. The card's performance is essentially a plateau, suggesting that its 1664 shading units, 104 TMUs, and 56 ROPs are balanced in a way that yields consistent, but not impressive, results across the board.
Memory Subsystem
The GTX 970 is equipped with 4 GB of GDDR5 memory on a 256-bit bus, providing a bandwidth of 224.4 GB/s. This configuration was considered ample at its release, but modern high-resolution textures can strain the capacity. The memory operates at a 1753 MHz clock, which translates to 7 Gbps effective data rate.
For high resolutions like 1440p or 4K, the data suggests that the 224.4 GB/s bandwidth is a limiting factor. While the 256-bit bus provides a solid foundation, the total bandwidth is modest by current standards. The 4 GB frame buffer is also a concern, as many contemporary titles at high settings can exceed this capacity, leading to texture pop-in or stuttering. The pixel rate of 65.97 GPixel/s and texture rate of 122.5 GTexel/s are consistent with a card designed for 1080p, where the memory subsystem is adequate for most titles of its era. At higher resolutions, the combination of limited VRAM and bandwidth means the card will likely underperform, as it cannot feed the GPU fast enough to maintain smooth frame rates.
Who Should Consider It
Given its benchmark scores and memory configuration, the GTX 970 is best suited for a specific niche. The data indicates it is a viable option for 1080p gaming at medium to high settings, particularly in titles that rely on DirectX 11 or older APIs. Its PassMark DirectX 11 score of 71 and DirectX 9 score of 143 suggest it handles legacy games with relative ease. Users with an older system looking to play esports titles or games from the 2015-2017 era will find the performance acceptable.
However, the low DirectX 12 score of 41 and the poor 3DMark Steel Nomad result of 369 signal that the card is not a good choice for modern AAA titles that require robust DX12 or Vulkan support. Gamers aiming for high refresh rates at 1440p or any 4K gaming should look elsewhere, as the 4 GB VRAM and 224.4 GB/s bandwidth will be insufficient. The card's power draw of 148 W, with a suggested 300 W PSU, makes it an easy drop-in upgrade for older systems that lack high-wattage power supplies. In summary, this is a card for budget-conscious users reviving an old rig for less demanding, older games, not for those seeking future-proofing or high-end performance.
FAQ
Q: How does the GTX 970 perform in modern DirectX 12 titles?
A: The PassMark DirectX 12 score is 41, which is the lowest of its API scores, and the 3DMark Steel Nomad DX12 score is 369, indicating very poor performance in modern DX12 workloads.
Q: What is the memory bandwidth and bus width of the GTX 970?
A: It has a 256-bit memory bus and a bandwidth of 224.4 GB/s, using 4 GB of GDDR5 memory.
Q: Is the GTX 970 suitable for 4K gaming?
A: No, the 4 GB VRAM and 224.4 GB/s bandwidth are not sufficient for high-resolution gaming. The data suggests it is best used at 1080p.
Q: What is the transistor count and die size of this GPU?
A: The GM204 chip contains 5,200 million transistors on a die size of 398 mm², manufactured on a 28 nm process.
Q: How does the GTX 970 compare to the GTX 650 Ti in average performance?
A: The GTX 970 is only 0.1% faster than the GTX 650 Ti in average benchmark scores, making them nearly identical in overall performance.
Q: What is the thermal design power (TDP) requirement?
A: The TDP is 148 W, and NVIDIA suggests a minimum 300 W power supply for the system.
How It Compares
NVIDIA GeForce GTX 650 Ti: The GTX 970 holds a razor-thin 0.1% performance lead over this older card. This indicates that, despite being a generation newer, the average benchmark scores are virtually indistinguishable, making the GTX 970 a marginal upgrade at best.
AMD Radeon R9 M360: The GTX 970 is 0.2% faster than this mobile-oriented chip. The data shows that in aggregate, the two are effectively equal in performance, highlighting that the GTX 970's desktop pedigree does not translate into a substantial advantage in this comparison.
NVIDIA GRID K2: The GTX 970 is 0.6% slower than this enterprise-focused dual-GPU card. This is a surprising result, as the GRID K2 is designed for virtualization, but the average scores suggest the GTX 970 cannot outpace it in synthetic benchmarks.
NVIDIA GeForce GTX 675MX: The GTX 970 trails this mobile GPU by 0.9%. The data clearly shows that the desktop GTX 970 does not have a meaningful performance edge over this older mobile part, with the delta well within the margin of error for benchmark variance.
The AMD Equivalent of GeForce GTX 970
Looking for a similar graphics card from AMD? The AMD Radeon RX 480 offers comparable performance and features in the AMD lineup.
Popular NVIDIA GeForce GTX 970 Comparisons
See how the GeForce GTX 970 stacks up against similar graphics cards from the same generation and competing brands.
Compare GeForce GTX 970 with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs