NVIDIA Tesla V100 DGXS 32 GB
NVIDIA graphics card specifications and benchmark scores
Tensor CoresAt a Glance
NVIDIANVIDIA Tesla V100 DGXS 32 GB Specifications
GPU Core
Shader units and compute resources
The NVIDIA Tesla V100 DGXS 32 GB 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 V100 DGXS 32 GB Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Tesla V100 DGXS 32 GB'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 V100 DGXS 32 GB by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's Tesla V100 DGXS 32 GB Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Tesla V100 DGXS 32 GB'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 V100 DGXS 32 GB by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the Tesla V100 DGXS 32 GB, 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 V100 DGXS 32 GB Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA Tesla V100 DGXS 32 GB 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.
Tesla V100 DGXS 32 GB Ray Tracing & AI
Hardware acceleration features
The NVIDIA Tesla V100 DGXS 32 GB includes dedicated hardware for ray tracing and AI acceleration. RT cores handle real-time ray tracing calculations for realistic lighting, reflections, and shadows in supported games. Tensor cores (NVIDIA) or XMX cores (Intel) accelerate AI workloads including DLSS, FSR, and XeSS upscaling technologies. These features enable higher visual quality without proportional performance costs, making the Tesla V100 DGXS 32 GB capable of delivering both stunning graphics and smooth frame rates in modern titles.
Volta Architecture & Process
Manufacturing and design details
The NVIDIA Tesla V100 DGXS 32 GB is built on NVIDIA's Volta 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 V100 DGXS 32 GB will perform in GPU benchmarks compared to previous generations.
Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA Tesla V100 DGXS 32 GB 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 V100 DGXS 32 GB to maintain boost clocks without throttling.
Tesla V100 DGXS 32 GB by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA Tesla V100 DGXS 32 GB 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 V100 DGXS 32 GB. 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 V100 DGXS 32 GB Product Information
Release and pricing details
The NVIDIA Tesla V100 DGXS 32 GB 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 V100 DGXS 32 GB 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 V100 DGXS 32 GB
NVIDIA Tesla V100 DGXS 32 GB is a dual-slot accelerator built on the Volta architecture, using a 12 nm process at TSMC with 21,100 million transistors on an 815 mm² die. It targets compute-heavy workloads rather than consumer gaming, with no display outputs and a PCIe 3.0 x16 interface. The card is end-of-life, released in March 2018, and sits at the 50th percentile among all GPUs in the database, with an average benchmark score of zero — meaning it is not evaluated in standard gaming or workstation suites here. Its specifications point to a specialized tool: 5,120 shading units, 320 texture mapping units, 128 ROPs, and 640 tensor cores, paired with 32 GB of HBM2 memory on a 4096-bit bus delivering 897.0 GB/s of bandwidth.
Benchmark Performance
The Tesla V100 DGXS 32 GB does not have standard benchmark scores recorded in this database, and its nearestRivals list is empty. As a result, direct percentage comparisons against competitor cards are unavailable. Instead, the data must be interpreted through its raw compute capabilities. The FP32 throughput is 15.67 TFLOPS, while FP16 reaches 31.33 TFLOPS at a 2:1 ratio — a doubling that indicates strong mixed-precision performance, typical for Volta’s design. Pixel fill rate is 195.8 GPixel/s, and texture fill rate is 489.6 GTexel/s, both respectable figures for a 2018-era accelerator, though they are not gaming-oriented metrics.
With a 50th percentile rank, the V100 sits exactly in the middle of the database’s GPU population — but that ranking likely reflects all GPUs, including consumer cards, so its position is not flattering for gaming. For compute, the numbers tell a different story: the 4096-bit memory bus and 897.0 GB/s bandwidth are far above consumer cards of its era, and the 32 GB HBM2 capacity allows large datasets to reside on-card. The FP16 performance of 31.33 TFLOPS is the standout figure, suggesting that workloads leveraging tensor cores and mixed precision will see substantial throughput gains over FP32-only execution. No deltaPct values exist for rivals, so every performance claim here is based on absolute specs, not relative comparisons.
Ray Tracing and Feature Set
The V100 DGXS 32 GB has no dedicated ray tracing cores — the rtCores field is null. Ray tracing, if performed, would rely on the shader units (5,120 of them) and the tensor cores (640) for denoising or acceleration, but there is no hardware-accelerated RT path. The API support includes DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, which are modern for the card’s release period but do not include any ray tracing-specific extensions beyond what those APIs offer generically. The tensor cores are the key feature: 640 of them, designed for matrix math, which drives the FP16 2:1 rate. This makes the card suited for AI inference and training, not for real-time ray tracing in games.
The card has no display outputs, confirming it is not intended for rendering frames to a screen. Its feature set is compute-first: tensor cores for deep learning, HBM2 for memory bandwidth, and a massive 32 GB pool for models or datasets. The 12 nm process and 21,100 million transistors show a large, power-hungry die, but the architecture prioritizes parallel throughput over graphics-specific features. Vulkan 1.4 support is notable for compute workloads that bypass traditional graphics pipelines, allowing direct access to the GPU’s resources.
How It Compares
Since the nearestRivals array is empty, there are no direct competitor comparisons available from the data. The V100 DGXS 32 GB stands alone in this database’s context, with no named rivals to measure against. Its percentile rank of 50 places it mid-pack, but that is a broad indicator, not a specific comparison. Without rival scores, the only way to contextualize it is against its own specifications: the 32 GB HBM2 memory and 897.0 GB/s bandwidth are far above typical consumer cards, but the lack of RT cores and display outputs makes it unsuitable for gaming. For compute, the FP16 rate of 31.33 TFLOPS is double the FP32 rate, a feature that consumer cards of the same era did not offer.
The absence of rivals means no deltaPct values exist to cite. The card’s position as a specialized accelerator is clear, but the data does not allow for a head-to-head assessment. The 50th percentile is a neutral score, reflecting an average standing across all GPUs — but that average includes cards with different purposes, so it carries little weight for a compute-focused product. The takeaway is that this card is not comparable to gaming GPUs in any meaningful sense, and the empty rivals list reinforces that. It is a niche product, and the data treats it as such.
Power and Cooling
The Tesla V100 DGXS 32 GB has a TDP of 250 W, which is moderate for a compute card of this size. The recommended PSU is 600 W, leaving headroom for the rest of the system. It requires no external power connectors — the powerConnectors field is listed as "None", meaning it draws all power from the PCIe 3.0 x16 slot. This is unusual for a 250 W card, suggesting the board is designed for server environments with specific power delivery. The slot width is dual-slot, so it will occupy two expansion slots in a chassis, and its dimensions are not listed, but the dual-slot design implies a substantial cooler.
Cooling is handled by a passive or blower-style solution, though the data does not specify. The 12 nm process and 21,100 million transistors generate heat, but the 250 W TDP is within range for a dual-slot cooler. The lack of power connectors means no 8-pin or 6-pin PCIe cables are needed, simplifying installation in systems that have limited cable management. The 600 W PSU recommendation is a minimum, not a suggestion for overclocking — the card has no game clock, only base (1297 MHz) and boost (1530 MHz), so power draw is fixed. For a server rack, this is a straightforward drop-in card, but for a desktop, the dual-slot size and no-output design require careful planning.
FAQ
Q: Does the Tesla V100 DGXS 32 GB support ray tracing?
A: No, it has no dedicated ray tracing cores. The rtCores field is null, so any ray tracing would be software-based on the 5,120 shading units, with tensor cores potentially assisting in denoising.
Q: What is the memory bandwidth of this card?
A: The V100 DGXS 32 GB has 897.0 GB/s of bandwidth, provided by 32 GB of HBM2 memory on a 4096-bit bus. The memory clock is 876 MHz, with an effective data rate of 1752 Mbps.
Q: Can this GPU output video to a monitor?
A: No, it has no display outputs. The card is designed for compute tasks only, such as AI training or scientific simulations, and cannot drive a display.
Q: What power connectors does it need?
A: None. The powerConnectors field is listed as "None", so it draws power exclusively from the PCIe 3.0 x16 slot. The recommended PSU is 600 W, but no additional cables are required.
Q: What is the FP16 performance compared to FP32?
A: FP16 performance is 31.33 TFLOPS, exactly double the FP32 rate of 15.67 TFLOPS. This 2:1 ratio indicates strong tensor core utilization for mixed-precision workloads.
Q: Is this card still in production?
A: No, it is end-of-life. The production status is listed as "End-of-life", with a release date of March 2018. It is part of the Tesla Volta generation, succeeding Tesla Pascal and preceding Tesla Turing.
Who Should Consider It
The Tesla V100 DGXS 32 GB is for compute professionals, not gamers. With no display outputs and no RT cores, it is useless for traditional gaming. The 50th percentile rank and zero benchmark scores confirm it is not evaluated in gaming or standard workstation tests. Instead, consider it if your workload relies on FP16 or tensor cores: the 31.33 TFLOPS FP16 rate and 640 tensor cores are its strengths. The 32 GB HBM2 memory with 897.0 GB/s bandwidth is ideal for large models or datasets that exceed consumer GPU memory.
For resolution-specific advice, this card does not target any resolution — it targets batch sizes and model complexity. If you run AI inference or training, the FP16 2:1 ratio means you can double throughput by using mixed precision. If you need a GPU for scientific computing with high memory capacity, the 32 GB pool is a key advantage. However, the 250 W TDP and dual-slot design mean it fits in servers with adequate cooling. The lack of power connectors simplifies installation, but the card is not for a typical desktop build. It is a purpose-built accelerator for a narrow set of tasks, and the data reflects that specialization.
Detailed benchmark scores and charts for the NVIDIA Tesla V100 DGXS 32 GB are below.
Benchmark Scores
No benchmark data available for this GPU.
Compare with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs