Select processor 1
Select processor 2
Intel Arc B570
NVIDIA L40

Intel Arc B570 vs NVIDIA L40. Specifications

User rating
star star star star star
Released
Intel Arc B570

Official family image; the appearance of individual versions may differ. Credit: Intel Corporation. Image source

Intel Arc B570
Released
Q3/2022
User rating
star star star star star
NVIDIA L40
NVIDIA L40

What's the best choice Intel Arc B570 or NVIDIA L40? Which graphics card is faster?

Compare the available specifications of these models.

Intel Arc B570Memory size 10 GB. Memory type GDDR6.

NVIDIA L40 has a base frequency of 2.25 GHz. Memory size 48 GB. Memory type GDDR6. Released in Q3/2022.

Differences

Videokards Reasons to consider
Intel Arc B570
Report a bug

Positions in all rankings

Common positions Intel Arc B570 GPU in popular benchmarks, for comparison with other models.

No data
Videokards Reasons to consider
NVIDIA L40
Report a bug
  • More memory

    380% more memory

    48 GB left arrow 10 GB

Positions in all rankings

Common positions NVIDIA L40 GPU in popular benchmarks, for comparison with other models.

No data

Specifications

Technical data
Intel Arc B570 Intel Arc B570
NVIDIA L40 NVIDIA L40
General info

Comparison of basic technical data of graphics cards Intel Arc B570 and NVIDIA L40, chip, information processing units.

  • Technology
    TSMC N5 left arrow -
  • Xe Vector Engines
    144 left arrow -
  • XMX Engines
    144 left arrow -
  • Ray Tracing Units
    18 left arrow -
  • Xe Cores
    18 left arrow -
  • GPU Chip
    Battlemage left arrow AD102
  • Architecture
    Xe2 left arrow -
  • Based on
    Intel Arc B570 left arrow -
  • RT Cores
    - left arrow 142
  • L2 Cache
    - left arrow 96 MB
  • L1 Cache
    - left arrow 128 KB
  • Texture Units
    - left arrow 568
  • Render Output Units
    - left arrow 192
  • Execution units
    - left arrow 18176
Memory settings

Video memory capacity, type, bus width and bandwidth describe different properties. These values alone do not determine graphics performance.

  • Memory Speed
    19 Gbps left arrow 18 Gbps
  • Memory Bandwidth
    380 GB/s left arrow -
  • Memory Bus
    160 bit left arrow -
  • Memory Type
    GDDR6 left arrow GDDR6
  • Memory Size
    10 GB left arrow 48 GB
  • Memory Interface
    - left arrow 384 bit
  • Memory Bandwith
    - left arrow 864.0 GB/s
  • Memory Clock
    - left arrow 2.25 GHz
Clock frequency

Published GPU clock frequencies describe different operating modes. Clock speed alone does not determine graphics performance.

  • Graphics Clock
    2500 MHz left arrow -
  • Boost Clock
    - left arrow 2.49 GHz
  • Base Clock
    - left arrow 0.735 GHz
Thermal Management

Connectors, the number of thermal watts emitted in normal mode and at overclocking.

  • TDP
    150 W left arrow 300 W
  • Suggested PSU
    - left arrow 700 W
  • Slot
    - left arrow Dual-slot
  • Power Connectors
    - left arrow 1x 16-pin
Interfaces

Connectivity and connections.

  • PCIe
    4.0 x8 left arrow -
  • DP Ports
    - left arrow 4x DisplayPort 1.4a
  • Max. Displays
    - left arrow 4
Technical data

Technical data that is used to its full potential in computer games.

  • Shader Model
    - left arrow 6.7
  • CUDA
    - left arrow 8.9
  • Vulkan
    - left arrow 1.3
  • OpenCL
    - left arrow 3.0
  • OpenGL
    - left arrow 4.6
  • DirectX
    - left arrow 12.2
  • Max. resolution
    - left arrow 3840x2160
Supported Video Codecs

Built-in support for video and image compression standards.

  • AV1
    Decode / Encode left arrow -
Dimensions

The difference in size, weight and slot of the compared devices

  • Width
    - left arrow 111 mm
  • Length
    - left arrow 267 mm
More information

Comparison of interfaces and release dates for GPU NVIDIA L40 and Intel Arc B570.

  • Verified on
    2026-09-30 left arrow -
  • Official source
    https://www.intel.com/content/www/us/en/products/sku/241676/intel-arc-b570-graphics/specifications.html left arrow -
  • Release date
    - left arrow Q3/2022
  • Structure size
    - left arrow 4 nm
  • GPU Interface
    - left arrow PCIe 4.0 x16
  • Architecture
    - left arrow Ada Lovelace
Theoretical Performance

  • FP64 (double)
    - left arrow 1.414 GFLOPS (1:64)
  • FP32 (float)
    - left arrow 90.52 TFLOPS
  • FP16 (half)
    - left arrow 90.52 TFLOPS (1:1)
  • Texture Rate
    - left arrow 1.414 GTexel/s
  • Pixel Rate
    - left arrow 478.1 GPixel/s

Benchmarks

Performance tests GPUs

No comparable benchmark results are available yet. Specifications alone do not determine which model is faster.

These are saved results from the earlier catalog. Measurement dates and test configurations were not recorded. Models with no comparable results are omitted.

-->

Latest comparisons