GeekRadar / The comparison desk

COMPARE.

GPU

Unspecified

RTX A6000

Graphics processor

Video memory: 48 GB^*
Memory bus: 384 bit^*
Rated memory bandwidth: 768 GB/s^*

Benchmark results

Geekbench GPU (reported compilation) · version unreported · CUDA224,604^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · CUDA224,604^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL200,330^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · OpenCL200,330^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · Vulkan109,243^*Platform unreported Compare results
Geekbench GPU (reported compilation) · version unreported · Vulkan109,243^*Platform unreported Compare results
PassMark · version unreported · G2Dmark832^*Platform unreported Compare results
PassMark · version unreported · G3Dmark22,122^*Platform unreported Compare results

Processing & platform

Architecture: Ampere^*
Process node: 8 nm^*
GPU base clock: 1,410 MHz^*
GPU boost clock: 1,800 MHz^*

Memory & storage

Video memory: 48 GB^*
Video memory type: GDDR6^*
Memory bus: 384 bit^*
Rated memory bandwidth: 768 GB/s^*

System configuration

Detailed specifications

Specifications 1 · 11 fields

Manufacturer: Nvidia^*
GFLOPS: 40,000^* GFLOPS
TDP: 300^*
Class: Workstation^*
Name: RTX A6000^*
Year: 2020^*
Fab: 8^*
Transistors (mln): 28,300^*
Die size: 628^*
Memory size: 49,152^*
Memory speed: 768^*

Specifications 2 · 19 fields

GPU architecture — NVIDIA RTX A6000 — 48 GB GDDR6

Ampere^*

Theoretical peak: BF16 tensor dense per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

154.8^* TFLOPS

Scope and conditions

Accumulation: FP32^*

Theoretical peak: FP16 tensor dense per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

154.8^* TFLOPS

Scope and conditions

Accumulation: FP32^*

Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

38.7^* TFLOPS

Native hardware support: FP4 tensor — NVIDIA RTX A6000 — 48 GB GDDR6

No^*

Native hardware support: FP6 tensor — NVIDIA RTX A6000 — 48 GB GDDR6

No^*

Native hardware support: FP8 tensor — NVIDIA RTX A6000 — 48 GB GDDR6

No^*

Theoretical peak: INT8 tensor dense per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

309.7^* TOPS

Theoretical peak: TF32 tensor dense per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

77.4^* TFLOPS

Physical configuration — NVIDIA RTX A6000 — 48 GB GDDR6

PCIe, full height, dual slot (4.4 in H x 10.5 in L)^*

GPU interconnect bandwidth — NVIDIA RTX A6000 — 48 GB GDDR6

112.5^* GB/s

GPU interconnect bandwidth per direction — NVIDIA RTX A6000 — 48 GB GDDR6

56.25^* GB/s

PCIe interface declaration — NVIDIA RTX A6000 — 48 GB GDDR6

PCIe Gen 4 x16^*

Maximum board power — NVIDIA RTX A6000 — 48 GB GDDR6

300^* W

Peak memory bandwidth per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

768^* GB/s

Memory interface width per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

384^* bit

Memory capacity per GPU — NVIDIA RTX A6000 — 48 GB GDDR6

48^* GB

Memory technology — NVIDIA RTX A6000 — 48 GB GDDR6

GDDR6^*

GPU model — NVIDIA RTX A6000 — 48 GB GDDR6

NVIDIA RTX A6000^*

Specifications 3 · 8 fields

Product Name: RTX A6000^*
GPU Chip: GA102^*
Released: Oct 5th, 2020^*
Bus: PCIe 4.0 x16^*
Memory: 48 GB, GDDR6, 384 bit^*
GPU clock: 1,410^* MHz
Memory clock: 2,000^* MHz
Shaders TMUs ROPs: 10752 / 336 / 112^*

Specifications 4 · 8 fields

Product Name: RTX A6000^*
GPU Chip: GA102^*
Released: Oct 5th, 2020^*
Bus: PCIe 4.0 x16^*
Memory: 48 GB, GDDR6, 384 bit^*
GPU clock: 1,410^* MHz
Memory clock: 2,000^* MHz
Shaders / TMUs / ROPs: 10752 / 336 / 112^*

Specifications 5 · 11 fields

Manufacturer: Nvidia^*
GFLOPS: 40,000^* GFLOPS
TDP: 300^*
Class: Workstation^*
Name: RTX A6000^*
Year: 2020^*
Fab: 8^*
Transistors (mln): 28,300^*
Die size: 628^*
Memory size: 49,152^*
Memory speed: 768^*

Specifications 6 · 61 fields

Brand: NVIDIA^*
Top BUS WIDTH: 384^* bit
Graphics Processor GPU Name: GA102^*
Graphics Processor Architecture: Ampere^*
Render Config SM Count: 84^*
Graphics Features CUDA: 8.6^*
Render Config Tensor Cores: 336^*
Graphics Processor Process Size: 8^* nm
Graphics Processor Transistors: 28,300 million^*
Graphics Processor Die Size: 628^* mm²
Graphics Card Release Date: Oct 5th, 2020^*
Graphics Card Generation: Workstation Ampere (Ax000)^*
Graphics Card Successor: Workstation Ada^*
Graphics Card Production: Active^*
Name: RTX A6000^*
Graphics Card Bus Interface: PCIe 4.0 x16^*
Clock Speeds Memory Clock: 2000 MHz 16 Gbps effective^*
Memory Memory Size: 48^* GB
Memory Memory Type: GDDR6^*
Memory Memory Bus: 384^* bit
Memory Bandwidth: 768^* GB/s
Render Config TMUs: 336^*
Top GRAPHICS PROCESSOR: GA102^*
Render Config ROPs: 112^*
Theoretical Performance Pixel Rate: 201.6 GPixel/s
Theoretical Performance Texture Rate: 604.8 GTexel/s
Board Design Slot Width: Dual-slot^*
Board Design TDP: 300^* W
Board Design Suggested PSU: 700^* W
Board Design Outputs: 4x DisplayPort 1.4a^*
Board Design Board Number: PG133 SKU 500^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2020.json^*
Graphics Processor Foundry: Samsung^*
Graphics Card Predecessor: Quadro Turing^*
Recommended Resolutions: Good:1920x1080 | Good:2560x1440 | Good:3840x2160^*
Graphics Card Launch Price: 4,649 USD^*
Board Design Length: 267 mm 10.5 inches^*
Board Design Power Connectors: 8-pin EPS^*
Graphics Processor Density: 45.1M / mm²^*
Board Design Height: 112 mm 4.4 inches^*
Top TMUS: 336^*
Graphics Processor Chip Package: BGA-3328^*
Top ROPS: 112^*
Clock Speeds Base Clock: 1,410^* MHz
Clock Speeds Boost Clock: 1,800^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 10,752^*
Render Config Shading Units: 10,752^*
Render Config L2 Cache: 6^* MB
Top MEMORY SIZE: 48^* GB
Theoretical Performance FP32 (float): 38.71^* TFLOPS
Theoretical Performance FP64 (double): 604.8 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 38.71 TFLOPS (1:1)
Graphics Card Availability: Dec 15th, 2020^*
Top MEMORY TYPE: GDDR6^*
Render Config RT Cores: 84^*

Specifications 7 · 24 fields

model: RTX A6000^*
base clock mhz: 1,410^* MHz
max boost clock mhz: 1,800^* MHz
bus type: GDDR6^*
bus width: 384^*
vram: 48^*
clock speed: 16,000^*
bandwith: 768^*
fp16: 38,710^*
fp32: 38,710^*
fp64: 1,209.67^*
price: 3,599^*
tdp: 300^*
nv link: 2-way NVLink^*
bus interface: PCIe 4.0 x16^*
eol: No^*
eol date: No^*
market: Professional^*
ecc equipped: Yes^*
architecture: Ampere^*
release date: 10/5/2020^*
tensor cores: 336^*
tensor core gen: 3rd Gen (Ampere)^*
cuda cores: 10,752^*

Specifications 8 · 5 fields

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

RTX A6000^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

CUDA

224,604^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

200,330^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Vulkan

109,243^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Specifications 9 · 14 fields

gpuName

RTX A6000^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

Manufacturer

Nvidia^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

Device

RTX A6000^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

G3Dmark

22,122^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

CUDA

224,604^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

G2Dmark

832^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

price

4,999.99^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

gpuValue

4.42^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

OpenCL

200,330^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

TDP

300^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

Vulkan

109,243^*

Scope and conditions

benchmark_context

suite: Geekbench GPU (reported compilation)^*
backend_columns: CUDA^*
Metal^*
OpenCL^*
Vulkan^*
test_configuration_verified: No^*
comparable: No^*

powerPerformance

73.74^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*

testDate

2,021^*

Scope and conditions

benchmark_context

suite: PassMark^*
test_configuration_verified: No^*
comparable: No^*