NVIDIA B300
We do not have performance data for the B300 for the 3DMark 11 Performance GPU benchmark.
We do not have performance per dollar data for the B300 for the 3DMark 11 Performance GPU benchmark.
Summary
About the NVIDIA B300 GPU
The NVIDIA B300 is a workstation graphics card that launched in Q3 2025. It is built on the Blackwell Ultra GPU microarchitecture (codename GB110) and is manufactured on a 5 nm process.
Memory
The B300 has 144 GB of HBM3e memory, with a 2,000 MHz memory clock and a 4,096 bit interface. This gives it a memory bandwidth of 4.1 Tb/s, which affects how fast it can transfer data to and from memory. GPU memory stores temporary data that helps the GPU with complex math and graphics operations. More memory is generally better, as not having enough can cause performance bottlenecks.
Cores and Clock Speeds
The B300 includes 18,944 CUDA cores, the processing units for handling parallel computing tasks. The GPU operates at a core clock speed of 1,665 MHz and can dynamically boost its clock speed up to 2,032 MHz. Complementing the processing units are 592 texture mapping units (TMUs) for efficient texture filtering and 24 render output units (ROPs) for pixel processing. Additionally, the GPU features 592 tensor cores optimized for AI-accelerated workloads.
Compatibility & Power Consumption
NVIDIA recommends a power supply of at least 1,800 W to handle the GPU's thermal design power (TDP) of 1,400 W.
General Info
General overview of the GPU, including details like its manufacturer, release date, launch price, and current production status.
| Info | Value |
|---|---|
| Manufacturer | NVIDIA |
| Architecture | Blackwell Ultra |
| Market Segment | Workstation |
| Release Date | Q3 2025 |
| Production Status | Active |
| Shop | Check Price |
Gaming Performance
Benchmark Performance
Technical Specs
Processor Details
General information about the graphics processing unit like its architecture, manufacturing process size, and transistor count. Newer GPU architectures generally bring efficiency improvements and may introduce technologies that enhance graphical capabilities.
| Spec | Value |
|---|---|
| Codename | GB110 |
| Architecture | Blackwell Ultra |
| Process Size | 5 nm |
| Transistors | 104,000 million |
Board Compatibility
Compatibility information like its slot size, bus interface, power consumption, and display support. These specs are useful for verifying compatibility with your motherboard, power supply, and monitor.
| Spec | Value |
|---|---|
| Bus Interface | PCIe 5.0 x16 |
| Thermal Design Power (TDP) | 1,400 W |
| Suggested PSU | 1,800 W |
| Outputs | No outputs |
Memory Details
Memory specifications like its capacity, bandwidth, and clock speeds. GPU memory stores graphics data like frames, textures, and shadows which helps display rendered images. These specs are crucial for graphics-intense applications like gaming and 3D modeling.
| Spec | Value |
|---|---|
| Memory Size | 144 GB |
| Memory Type | HBM3e |
| Memory Bandwidth | 4.1 Tb/s |
| Memory Clock | 2,000 MHz |
| Memory Interface | 4,096 bit |
| L1 Cache | 256 KB |
| L2 Cache | 50 MB |
Cores & Clock Speeds
Processing power information like its cores and clock speed. These specs impact how fast they can process graphics. Each type of core or component serves a specific computational purpose.
| Spec | Value |
|---|---|
| CUDA Cores | 18,944 |
| Stream Multiprocessors (SM) | 148 |
| Texture Mapping Units (TMU) | 592 |
| Render Output Units (ROP) | 24 |
| Tensor Cores | 592 |
| Core Clock Speed | 1,665 MHz |
| Core Clock Speed (Boost) | 2,032 MHz |
Theoretical Performance
Theoretical performance numbers derived from the raw specifications of the different components like core count and clock speeds. While these provide a glimpse into peak processing power, they do not represent real-world performance.
| Spec | Value |
|---|---|
| Pixel Fill Rate | 48.77 GPixel/s |
| Texture Fill Rate | 1,202.9 GTexel/s |
| FP32 Performance | 76.99 TFLOPS |
| FP64 Performance | 1,202.9 GFLOPS |
API Support
Graphics API versions supported by this graphics card. APIs evolve over time, introducing new features and functionalities. Older GPUs may not support recent versions.
| Spec | Value |
|---|---|
| OpenCL | 3.0 |
* Performance rating, performance per dollar, and rankings are based on the 3DMark 11 Performance GPU benchmark and MSRP.