GEFORCE

NVIDIA GB10

NVIDIA graphics card specifications and benchmark scores

128 GB
VRAM
2418
MHz Boost
140W
TDP
256
Bus Width
Ray Tracing 🤖Tensor Cores

NVIDIA GB10 Specifications

⚙️

GB10 GPU Core

Shader units and compute resources

The NVIDIA GB10 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.

Shading Units
6,144
Shaders
6,144
TMUs
384
ROPs
48
SM Count
48
⏱️

GB10 Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the GB10'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 GB10 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

Base Clock
1665 MHz
Base Clock
1,665 MHz
Boost Clock
2418 MHz
Boost Clock
2,418 MHz
Memory Clock
1067 MHz 8.5 Gbps effective
GDDR GDDR 6X 6X

NVIDIA's GB10 Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GB10'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.

Memory Size
128 GB
VRAM
131,072 MB
Memory Type
LPDDR5X
VRAM Type
LPDDR5X
Memory Bus
256 bit
Bus Width
256-bit
Bandwidth
273.2 GB/s
💾

GB10 by NVIDIA Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the GB10, 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.

L1 Cache
256 KB (per SM)
L2 Cache
50 MB
📈

GB10 Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the NVIDIA GB10 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.

FP32 (Float)
29.71 TFLOPS
FP64 (Double)
464.3 GFLOPS (1:64)
FP16 (Half)
29.71 TFLOPS (1:1)
Pixel Rate
116.1 GPixel/s
Texture Rate
928.5 GTexel/s

GB10 Ray Tracing & AI

Hardware acceleration features

The NVIDIA GB10 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 GB10 capable of delivering both stunning graphics and smooth frame rates in modern titles.

RT Cores
48
Tensor Cores
384
🏗️

Blackwell 2.0 Architecture & Process

Manufacturing and design details

The NVIDIA GB10 is built on NVIDIA's Blackwell 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 GB10 will perform in GPU benchmarks compared to previous generations.

Architecture
Blackwell 2.0
GPU Name
GB20B
Process Node
5 nm
Foundry
TSMC
🔌

NVIDIA's GB10 Power & Thermal

TDP and power requirements

Power specifications for the NVIDIA GB10 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 GB10 to maintain boost clocks without throttling.

TDP
140 W
TDP
140W
Power Connectors
None
Suggested PSU
300 W
📐

GB10 by NVIDIA Physical & Connectivity

Dimensions and outputs

Physical dimensions of the NVIDIA GB10 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.

Slot Width
IGP
Length
150 mm 5.9 inches
Height
51 mm 2 inches
Bus Interface
PCIe 5.0 x16
Display Outputs
1x HDMI
Display Outputs
1x HDMI
🎮

NVIDIA API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the NVIDIA GB10. 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.

OpenCL
3.0
CUDA
12.1
📦

GB10 Product Information

Release and pricing details

The NVIDIA GB10 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 GB10 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.

Manufacturer
NVIDIA
Release Date
Oct 2025
Launch Price
3,999 USD
Production
Active
Predecessor
Server Hopper
Successor
Server Rubin

GB10 Benchmark Scores

📊

No benchmark data available for this GPU.

About NVIDIA GB10

The NVIDIA GB10 graphics card enters the market as a formidable enterprise and data center solution, defined by its staggering 128 GB of LPDDR5X memory. With a launch price of $3,999, the price-to-performance ratio is heavily skewed towards workloads requiring immense memory bandwidth, such as large language model inference and scientific simulations, rather than traditional gaming. Positioned firmly in the professional compute segment, the NVIDIA GB10 leverages the advanced Blackwell 2.0 architecture on a 5nm process for exceptional efficiency. Its 140W TDP is remarkably restrained for a card of this capability, suggesting sophisticated power management. The lack of consumer-grade benchmark data underscores its specialized nature, making raw specifications the primary metric for evaluation.

  • Unprecedented 128 GB VRAM capacity for massive datasets.
  • PCIe 5.0 x16 interface ensures maximum platform bandwidth.
  • Targeted at AI research and high-performance computing (HPC).
  • High initial investment justified by professional application throughput.
  • Not intended for or competitive in the consumer gaming market.

When considering segment placement, the NVIDIA GB10 is not a competitor to mainstream GeForce cards but a specialized tool for server racks and high-end workstations. Its longevity is virtually guaranteed by the forward-looking memory pool and PCIe 5.0 support, ensuring relevance for multi-year deployment cycles in rapidly evolving fields like generative AI. The card's architecture is designed for sustained computational loads, promising reliability under constant operation. For organizations, the investment in the NVIDIA GB10 is an investment in computational infrastructure capable of handling next-generation software demands. This positions it as a strategic purchase for future-proofing critical workflows.

  • Dominates in memory-intensive professional applications.
  • Architectural efficiency leads to lower total cost of ownership for data centers.
  • Lack of gaming-oriented features like real-time ray tracing acceleration.
  • Expected lifecycle surpasses consumer GPUs due to its target market.
  • Performance scalability in multi-GPU configurations is a key advantage.

Build recommendations for the NVIDIA GB10 necessitate a supporting ecosystem capable of harnessing its power, including a robust PCIe 5.0 compliant motherboard and a high-wattage, stable power supply. System cooling is paramount, as even with a 140W TDP, dense server deployments require excellent airflow or liquid cooling solutions to maintain optimal boost clocks up to 2418 MHz. The primary use case for the NVIDIA GB10 graphics card is within a dedicated computational server or a workstation built for software development and AI model training. It is ill-suited for standard desktop gaming PCs, both physically and functionally. Ultimately, this card is a precision instrument for a specific class of user, where its value is measured in productivity and research breakthroughs, not frames per second.

  • Requires a server-grade or HEDT platform with PCIe 5.0 support.
  • Adequate case ventilation or server rack cooling is non-negotiable.
  • Pair with high-core-count CPUs to avoid system bottlenecks.
  • Driver support will be focused on enterprise and developer frameworks.
  • Ideal for virtualization environments and cloud computing instances.

The AMD Equivalent of GB10

Looking for a similar graphics card from AMD? The AMD Radeon RX 7700 offers comparable performance and features in the AMD lineup.

AMD Radeon RX 7700

AMD • 16 GB VRAM

View Specs Compare

Popular NVIDIA GB10 Comparisons

See how the GB10 stacks up against similar graphics cards from the same generation and competing brands.

Compare GB10 with Other GPUs

Select another GPU to compare specifications and benchmarks side-by-side.

Browse GPUs