A10 PCIe: specs and benchmarks

Summary

NVIDIA started A10 PCIe sales 12 April 2021. This is an Ampere architecture desktop card based on 8 nm manufacturing process and primarily aimed at designers. 24 GB of GDDR6 memory clocked at 1.56 GHz are supplied, and together with 384 Bit memory interface this creates a bandwidth of 600.2 GB/s.

Compatibility-wise, this is a single-slot graphics card attached via PCIe 4.0 x16 interface. Its manufacturer default version has a length of 267 mm. 8-pin EPS power connector is required, and power consumption is at 150 Watt.

Primary details

Some basic facts about A10 PCIe: architecture, market segment, release date etc.

Place in the ranking	not rated
Place by popularity	not in top-100
Architecture	Ampere (2020−2024)
GPU code name	GA102
Market segment	Workstation
Release date	12 April 2021 (3 years ago)

Detailed specifications

A10 PCIe's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of A10 PCIe's performance, but for precise assessment you have to consider its benchmark and gaming test results.

Pipelines / CUDA cores	9216	of 21760 (GeForce RTX 5090)
Core clock speed	885 MHz	of 2670 MHz (Arc B580)
Boost clock speed	1695 MHz	of 3599 MHz (Radeon RX 7990 XTX)
Number of transistors	28,300 million	of 208,000 million (B200 SXM 192 GB)
Manufacturing process technology	8 nm	of 3 nm (Arc Graphics 140V)
Power consumption (TDP)	150 Watt	of 2400 Watt (Data Center GPU Max Subsystem)
Texture fill rate	488.2	of 2,554 (Radeon Instinct MI300X)
Floating-point processing power	31.24 TFLOPS	of 109.7 (GeForce RTX 5090)
ROPs	96	of 192 (Radeon RX 7900 XTX)
TMUs	288	of 1280 (Data Center GPU Max NEXT)
Tensor Cores	288	of 1216 (Radeon Instinct MI300X)
Ray Tracing Cores	72	of 170 (GeForce RTX 5090)

Form factor & compatibility

This section provides details about the physical dimensions of A10 PCIe and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).

Interface	PCIe 4.0 x16
Length	267 mm
Width	1-slot
Supplementary power connectors	8-pin EPS

VRAM capacity and type

Parameters of memory installed on A10 PCIe: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.

Memory type	GDDR6
Maximum RAM amount	24 GB	of 294912 (Radeon Instinct MI325X)
Memory bus width	384 Bit	of 8192 Bit (Radeon Instinct MI250X)
Memory clock speed	1563 MHz	of 20000 (RTX 5000 Ada Generation Mobile)
Memory bandwidth	600.2 GB/s	of 5,171 GB/s (Radeon Instinct MI300X)

Connectivity and outputs

Types and number of video connectors present on A10 PCIe. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.

Display Connectors

No outputs

API compatibility

APIs supported by A10 PCIe, sometimes including their particular versions.

DirectX	12 Ultimate (12_2)
Shader Model	6.6
OpenGL	4.6
OpenCL	3.0
Vulkan	1.2
CUDA	8.6

Benchmark performance

Synthetic benchmark performance of A10 PCIe. The combined score is measured on a 0-100 point scale.

---

---