NVIDIA Tesla K20m
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA Tesla K20m Specifications
GPU Core
Shader units and compute resources
The NVIDIA Tesla K20m 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.
Tesla K20m Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Tesla K20m'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 Tesla K20m by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's Tesla K20m Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Tesla K20m'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.
Tesla K20m by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the Tesla K20m, 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.
Tesla K20m Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA Tesla K20m 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.
Kepler Architecture & Process
Manufacturing and design details
The NVIDIA Tesla K20m is built on NVIDIA's Kepler 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 Tesla K20m will perform in GPU benchmarks compared to previous generations.
Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA Tesla K20m 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 Tesla K20m to maintain boost clocks without throttling.
Tesla K20m by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA Tesla K20m 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 Tesla K20m. 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.
Tesla K20m Product Information
Release and pricing details
The NVIDIA Tesla K20m 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 Tesla K20m by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
About NVIDIA Tesla K20m
The NVIDIA Tesla K20m is a Tesla Kepler (Kxx) generation compute card built on the GK110 chip. TSMC manufactures it on a 28 nm process, with 7,080 million transistors on a 561 mm² die and a transistor density of 12.6M per mm². The database lists an average benchmark score of 19011, placing it at the 61st percentile of all GPUs. Its Geekbench OpenCL score is 16085 and its Geekbench Vulkan score is 21936. It launched on 2013-01-04 as the successor to Tesla Fermi and the predecessor to Tesla Maxwell, with launch MSRP 3,199 USD. The card is end-of-life and has no display outputs.
Memory Subsystem
The memory subsystem consists of 5 GB of GDDR5 on a 320-bit bus, providing 208.0 GB/s of bandwidth. The memory clock is listed at 1300 MHz, or 5.2 Gbps effective. That is a coherent GDDR5 configuration for a GPU of this generation, but the capacity is the more immediate constraint for high-resolution workloads.
At high resolutions, the working set must fit inside 5 GB. Textures, render targets, and compute buffers all draw from that same pool. Once the working set exceeds 5 GB, the card cannot proceed without spilling data somewhere else. The 208.0 GB/s bandwidth is the pipe through which those 5 GB are accessed, and it is high enough for the GK110 compute resources to stay occupied when the workload is sized correctly. For offscreen rendering or compute at high resolutions, 5 GB is the hard ceiling.
Ray Tracing and Feature Set
No RT cores or tensor cores are listed for the Tesla K20m, so there is no dedicated hardware for ray tracing or tensor-accelerated AI work. The feature set is defined by the Kepler API support: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. These APIs allow general-purpose OpenCL and Vulkan compute paths, which are the primary way this card will actually execute work.
The GK110 configuration includes 2496 shading units, 208 TMUs, and 40 ROPs. The listed throughput figures are 36.71 GPixel/s, 146.8 GTexel/s, and 3.524 TFLOPS for FP32. With no display outputs, none of that rendering pipeline can be used to drive a monitor; the pixel rate and texture rate apply to offscreen rendering or compute workloads.
How It Compares
The Tesla K20m sits in a tight cluster around its nearest rivals. Its average benchmark score is 19011, and the four closest cards are separated by small delta percentages.
NVIDIA GeForce RTX 4050 Mobile: The RTX 4050 Mobile averages 19049, with a delta of -0.2%. The K20m trails by 0.2% in average score, so the two are effectively matched in this dataset.
AMD Radeon 780M: The Radeon 780M averages 19057, also showing a delta of -0.2%. Again, the K20m is 0.2% behind, placing it in the same performance band as this modern GPU.
NVIDIA Quadro K6000: The Quadro K6000 averages 19090, with a delta of -0.4%. The K20m is 0.4% behind, making the K6000 the closest rival above it in average score.
NVIDIA Tesla K80: The Tesla K80 averages 18866, with a delta of 0.8%. The K20m is 0.8% ahead of the K80, which is the only rival in this nearest set that the K20m leads by a measurable margin.
The overall picture is one of near parity: the K20m is within 0.4% of the two NVIDIA cards above it and within 0.2% of the mobile and integrated-class cards, while holding an 0.8% advantage over the K80.
FAQ
Q: Does the Tesla K20m support Vulkan?
A: Yes. The listed Vulkan version is 1.2.175. It also supports OpenGL 4.6 and DirectX 12 (11_0).
Q: Does it have RT cores or tensor cores?
A: No. Neither RT cores nor tensor cores are listed for the K20m, so there is no dedicated hardware for those acceleration paths.
Q: How much memory does the card have, and what is its bandwidth?
A: It has 5 GB of GDDR5 on a 320-bit bus, with 208.0 GB/s of bandwidth. The memory clock is 1300 MHz, or 5.2 Gbps effective.
Q: What power connectors does it require?
A: The card uses 1x 6-pin + 1x 8-pin PCIe power connectors. Its TDP is 225 W, and the database recommends a 550 W PSU.
Q: Can the Tesla K20m drive a display?
A: No. Display outputs are listed as “No outputs,” so it is a headless compute card.
Q: What are the benchmark scores for the Tesla K20m?
A: The Geekbench OpenCL score is 16085, the Geekbench Vulkan score is 21936, and the average benchmark score is 19011.
Who Should Consider It
The Tesla K20m is for users with headless OpenCL or Vulkan compute workloads, not for anyone who needs to attach a monitor. With no display outputs, every task must be executed through the compute API rather than presented on screen. Its 19011 average score and 61st percentile position put it in the same performance class as the RTX 4050 Mobile and Radeon 780M, so workloads that run on those platforms give a useful reference for expected average throughput.
The practical ceiling is the combination of 5 GB of memory and 3.524 TFLOPS of FP32 compute. A workload that fits inside 5 GB and is not compute-heavy beyond that FP32 figure will extract most of what the card offers. High-resolution work should be planned around the 5 GB capacity: if the render target plus all intermediate buffers fit, the memory subsystem is sufficient; if not, this card will not handle it. The 61st percentile makes clear that it is not a top-tier accelerator, but within its memory and compute limits it remains a usable headless compute board.
Power and Cooling
The TDP is 225 W, and the database lists a suggested PSU of 550 W. Power is delivered through 1x 6-pin + 1x 8-pin PCIe power connectors. The card is dual-slot, and its length is listed as 267 mm, or 10.5 inches, so physical clearance should be checked against that dimension. It connects through PCIe 2.0 x16. Production status is end-of-life, meaning this is older hardware rather than an active product line.
Detailed benchmark scores and charts for the NVIDIA Tesla K20m are below.
Benchmark Scores
geekbench_openclSource
Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how NVIDIA Tesla K20m 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 Performersgeekbench_vulkanSource
Geekbench Vulkan tests GPU compute using the modern low-overhead Vulkan API. This shows how NVIDIA Tesla K20m performs with next-generation graphics and compute workloads.
Top 5 Performers
Nearby Performers
Popular NVIDIA Tesla K20m Comparisons
See how the Tesla K20m stacks up against similar graphics cards from the same generation and competing brands.
Compare with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs