NVIDIA GeForce GT 620
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA GeForce GT 620 Specifications
GeForce GT 620 GPU Core
Shader units and compute resources
The NVIDIA GeForce GT 620 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.
GT 620 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the GeForce GT 620'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 GT 620 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's GeForce GT 620 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce GT 620'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 GT 620 by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the GT 620, 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.
GT 620 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce GT 620 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.
Fermi Architecture & Process
Manufacturing and design details
The NVIDIA GeForce GT 620 is built on NVIDIA's Fermi 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 GT 620 will perform in GPU benchmarks compared to previous generations.
NVIDIA's GeForce GT 620 Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA GeForce GT 620 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 GT 620 to maintain boost clocks without throttling.
GeForce GT 620 by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA GeForce GT 620 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 GT 620. 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 GT 620 Product Information
Release and pricing details
The NVIDIA GeForce GT 620 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 GT 620 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
GeForce GT 620 Benchmark Scores
geekbench_openclSource
Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how NVIDIA GeForce GT 620 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.
Top 5 Performers
Top 5 PerformersNearby Performers
Nearby PerformersAbout NVIDIA GeForce GT 620
The NVIDIA GeForce GT 620 is a Fermi-architecture entry-level card from the GeForce 600 generation, built on TSMC's 40 nm process with 585 million transistors on a 116 mm² die. Its benchmark data places it at the 7th percentile of all GPUs, with an average Geekbench OpenCL score of 1560. This is not a card for modern gaming; it is a legacy part whose performance sits just above the absolute floor of the database.
Power and Cooling
The GT 620 carries a TDP of 49 W, which is remarkably low by any standard. This makes it a trivial addition to almost any system, as the data indicates it draws power entirely from the motherboard slot. The card lists "None" for power connectors, meaning there is no 6-pin or 8-pin PEG cable required. The suggested PSU is a 200 W unit, which is a figure that most basic office or home pre-builts from the last two decades will comfortably meet.
The cooling solution is a single-slot design, and the physical length is 145 mm (5.7 inches). This makes the card physically compact and suitable for small form factor cases, though the modest 2.800 GPixel/s pixel rate and 11.20 GTexel/s texture rate mean it will never generate significant heat in practice. For a builder resurrecting an old system, the absence of any auxiliary power requirement is the key takeaway, you can slot this into any working PCIe 2.0 x16 lane without concern for PSU headroom or cable routing.
Ray Tracing and Feature Set
This card has no ray tracing cores and no tensor cores. The architecture is Fermi, which predates any hardware acceleration for ray tracing by nearly a decade. The data shows no RT core or tensor core counts because they do not exist on this die. Similarly, the Vulkan API support is listed as null, so any modern title relying on Vulkan will not run with that backend.
The API support is limited to DirectX 12 (11_0) and OpenGL 4.6. The DirectX 12 support is feature-level 11_0, which is a compatibility layer rather than full hardware implementation. In practical terms, this means the card can technically initialize DirectX 12 titles, but the underlying hardware lacks the shader capabilities to execute them at playable rates. The FP32 performance is 268.8 GFLOPS, which is the raw compute ceiling. For any workload involving modern shaders, this is insufficient. The display outputs are 1x DVI, 1x HDMI 1.3a, and 1x VGA, which reflects the era of its release, useful for legacy monitors but lacking modern display standards.
Who Should Consider It
The benchmark score of 1560 in Geekbench OpenCL places this card at the 7th percentile of all GPUs. This is a decisive data point: it is not a gaming card for any resolution or settings combination that involves 3D acceleration. The nearest rival data shows it is effectively tied with the AMD Radeon HD 6570 (0.4% ahead) and the AMD Radeon HD 7570 (0.2% ahead). These are all cards from the same vintage, and none are viable for modern titles.
The only practical use case is basic 2D desktop acceleration, video output, or as a diagnostic card for testing a motherboard. For 1080p video playback, the card's 14.40 GB/s bandwidth and 1024 MB of DDR3 memory might suffice for older codecs, but modern 4K streams will struggle. The FP32 figure of 268.8 GFLOPS is roughly a hundredth of what a modern entry-level card offers, so any compute task is out of the question. If you need a card to display a desktop at 1920x1080 for office work, it will do that. If you intend to game, the data is unambiguous: the 7th percentile score indicates failure across the board.
FAQ
Q: Can this card run modern games at low settings?
A: No. The Geekbench OpenCL score of 1560 places it at the 7th percentile of all GPUs, and its nearest rivals (AMD Radeon HD 6570, HD 7570) are similarly dated. The 268.8 GFLOPS FP32 throughput is insufficient for any modern game engine.
Q: What power supply do I need?
A: The suggested PSU is 200 W. The card draws 49 W TDP and requires no power connectors, so it draws all its power from the PCIe slot.
Q: Does this card support hardware ray tracing?
A: No. The GT 620 has no ray tracing cores and no tensor cores. It is based on the Fermi architecture, which predates RT hardware.
Q: What is the memory configuration?
A: It has 1024 MB of DDR3 memory on a 64-bit bus, yielding a bandwidth of 14.40 GB/s. The memory clock is 900 MHz (1800 Mbps effective).
Q: Which APIs are supported?
A: DirectX 12 (11_0) and OpenGL 4.6. Vulkan is not supported.
Q: How does it compare to the NVIDIA GeForce RTX 3060 8 GB?
A: The GT 620 scores 1560, while the RTX 3060 8 GB scores 1577. The delta is -1.1%, meaning the GT 620 is actually 1.1% behind the RTX 3060 in this specific OpenCL test, despite the massive generational gap.
Benchmark Performance
The sole benchmark result is Geekbench OpenCL, where the GT 620 scores 1560. The average benchmark score is identical at 1560, indicating no variance across runs. Against its nearest rivals, the data shows a tightly clustered group. The AMD Radeon HD 6570 scores 1554, which is 0.4% slower than the GT 620. The AMD Radeon HD 7570 scores 1557, which is 0.2% slower. The AMD FirePro V3900 scores 1564, which is 0.3% faster. These deltas are within noise margins, the GT 620 is effectively identical to all three cards in raw compute throughput.
The most striking comparison is against the NVIDIA GeForce RTX 3060 8 GB, which scores 1577. The delta is -1.1%, meaning the GT 620 is only 1.1% behind a modern card that costs orders of magnitude more and draws vastly more power. This is a quirk of the Geekbench OpenCL test, which apparently does not scale well with the RTX 3060's architecture. The data must be read carefully: a 1.1% delta does not mean the GT 620 is nearly as capable. The percentile rank of 7 versus the RTX 3060's much higher ranking tells the real story. In any real-world workload, the RTX 3060 would outperform the GT 620 by several hundred percent, but the benchmark data as provided shows only this narrow margin. The practical takeaway is that this OpenCL score is not a proxy for gaming performance; it is a synthetic compute metric that happens to favor older, simpler architectures in this specific test.
Memory Subsystem
The GT 620 is equipped with 1024 MB of DDR3 memory, which is a generation behind even the GDDR5 standard of its time. The memory bus is 64 bits wide, which is half the width of typical cards from that era. This narrow bus is the primary bottleneck. The bandwidth is 14.40 GB/s, derived from a memory clock of 900 MHz (1800 Mbps effective). At 1920x1080, this bandwidth is sufficient for 2D framebuffer operations but collapses under any 3D texture load.
The pixel rate is 2.800 GPixel/s and the texture rate is 11.20 GTexel/s. These figures are constrained by the 4 ROPs and 16 TMUs. For high resolutions, the data is clear: the 64-bit bus and 14.40 GB/s bandwidth are the limiting factors. Modern games at 1080p require bandwidth in excess of 100 GB/s, so this card is over seven times short of that threshold. The 1024 MB VRAM is also a hard cap, many modern titles exceed 4 GB at minimum settings. For any resolution above 1366x768, the memory subsystem will saturate immediately, causing frame drops and texture thrashing. The card is fundamentally a 720p or lower resolution part, and even then, only for titles from its release generation.
Compare GeForce GT 620 with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs