GeekRadar / The comparison desk
COMPARE.
GPUNVIDIA A2
Graphics processor
- Video memory
- 16 GB*
- Memory bus
- 128 bit*
- Rated memory bandwidth
- 200.10 GB/s*
Rendering performance
Three-scene Blender rendering throughput. Versions, operating systems and rendering backends remain separate. This is not a gaming score.
Community submissions; cooling, power limits and system configuration can affect results.
Graphics & compute benchmarks
GFXBench, GLBenchmark and CompuBench results retain the tested system, API, operating system and resolution. Offscreen tests fix the render resolution; onscreen results also reflect the display workload. These historical submissions do not establish performance in current games.
4K Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 3840 x 2160 / offscreen · fps
Higher is better.
NVIDIA A2
34.24* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins High Tier OffscreenWindows / DirectX 12 / 2560 x 1440 / offscreen · fps
Higher is better.
NVIDIA A2
78.90* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins Normal Tier OffscreenWindows / DirectX 12 / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA A2
205.97* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins Normal Tier OffscreenWindows / Vulkan / 1920 x 1080 / offscreen · fps
Higher is better.
NVIDIA A2
219.70* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins High TierWindows / DirectX 12 / 1920 x 1200 / onscreen · fps
Higher is better.
NVIDIA A2
121.86* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins Normal TierWindows / DirectX 12 / 1920 x 1200 / onscreen · fps
Higher is better.
NVIDIA A2
184.89* fps
NVIDIA A2
Host configuration not reported.
Aztec Ruins Normal TierWindows / Vulkan / 1280 x 800 / onscreen · fps
Higher is better.
NVIDIA A2
130.30* fps
NVIDIA A2
Host configuration not reported.
Median results, not the best run. Sample counts and individual test dates are unreported. Different systems using the same GPU remain separate configurations.
Benchmark results
- Geekbench GPU (reported compilation) · version unreported · OpenCL35,467*Platform unreported Compare results
- Geekbench GPU (reported compilation) · version unreported · Vulkan34,563*Platform unreported Compare results
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Blender Cycles / classroomOPTIX / Linux · 3.5.0 · samples/min
NVIDIA A2
238.26 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / Complete suiteOPTIX / Linux · 3.5.0 · samples/min
NVIDIA A2
988.82 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
- 25th percentile
- 976.89238162733
- 75th percentile
- 990.54602777151
Blender Cycles / junkshopOPTIX / Linux · 3.5.0 · samples/min
NVIDIA A2
290.22 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Blender Cycles / monsterOPTIX / Linux · 3.5.0 · samples/min
NVIDIA A2
455.68 samples/min
5 submissions · median result
Latest submission:- Rendering backend
- OPTIX
- Operating system
- Linux
- Statistic
- Median
- Evaluation type
- community rendering submissions
Processing & platform
- Architecture
- Ampere
- Manufacturing process
- 8 nm
- Process node
- 8 nm
- GPU cores
- 1,280*
- Graphics interface
- PCIe 4.0 x8*
- Reported chip die area
- 200 mm²*
- Transistors
- 8,700 million*
- GPU L2 cache
- 2 MB*
- Graphics processor
- GA107*
- Texture mapping units
- 40*
- Raster output units
- 32*
- Streaming multiprocessors
- 10*
- Tensor cores
- 40*
- Ray tracing cores
- 10*
- Chip foundry
- Samsung*
- Card or module format
- Single-slot*
- Declared GPU TDP
- 60 W*
- Suggested system PSU
- 250 W*
- External power connectors
- None*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenGL
- 4.6*
- OpenCL
- 3.0*
- Vulkan
- 1.4*
- CUDA compute capability
- 8.6*
- Shader model
- 6.9*
Memory & storage
- Memory options
- 16*
- Video memory
- 16 GB*
- Video memory type
- GDDR6*
- Memory bus
- 128 bit*
- Rated memory bandwidth
- 200.10 GB/s*
Power specifications
- Thermal design power
- 60 W*
System configuration
Detailed specifications
Specifications 1 · 19 fields
- GPU architecture — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- Ampere*
- Theoretical peak: BF16 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 18* TFLOPS
- Theoretical peak: FP16 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 18* TFLOPS
- Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 4.5* TFLOPS
- Native hardware support: FP4 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- No*
- Native hardware support: FP64 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- No*
- Native hardware support: FP6 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- No*
- Native hardware support: FP8 tensor — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- No*
- Theoretical peak: INT8 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 36* TOPS
- Theoretical peak: TF32 tensor dense per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 9* TFLOPS
- Physical configuration — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- PCIe, low-profile, single-slot*
- Native hardware support for GPU interconnect — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- No*
- PCIe interface declaration — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- PCIe Gen4 x8*
- Maximum board power — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 60* W
- Peak memory bandwidth per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 200* GB/s
- Memory interface width per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 128* bit
- Memory capacity per GPU — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- 16* GB
- Memory technology — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- GDDR6*
- GPU model — NVIDIA A2 Tensor Core GPU — 16 GB GDDR6
- NVIDIA A2 Tensor Core GPU*
Specifications 2 · 30 fields
- proc transistors
- 8,700 million*
- proc die size
- 200* mm²
- cores
- 1,280*
- tensor cores
- 40*
- rt cores
- 10*
- sm count
- 10*
- base clock
- 1,440*
- boost clock
- 1,770*
- memory clock
- 1,563*
- ram
- 16*
- name
- NVIDIA A2*
- ram type
- GDDR6*
- bus width
- 128*
- bus interface
- PCIe 4.0 x8*
- ram bandwidth
- 200.1* GB/s
- fp16 performance
- 4.531*
- fp32 performance
- 4.531*
- fp64 performance
- 0.0708*
- tdp
- 60* W
- suggested psu
- 250* W
- slot width
- Single-slot*
- api cuda
- 8.6*
- is retail board
- No*
- gpi value
- 3.96*
- vendor
- nvd*
- manufacturer
- NVIDIA*
- arch name
- Ampere*
- card release date
- 2021-11-10*
- proc foundry
- Samsung*
- proc process size
- 8* nm
Specifications 3 · 40 fields
- CUDA compute capability
- 8.6*
- DirectX / feature level
- 12 Ultimate (12_2)*
- OpenCL
- 3.0*
- OpenGL
- 4.6*
- Shader model
- 6.9*
- Vulkan
- 1.4*
- Architecture
- Ampere*
- Graphics interface
- PCIe 4.0 x8*
- Memory bus
- 128* bit
- Reported shader processors
- 1,280*
- Reported theoretical FP16 peak
- 4.531* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP32 peak
- 4.531* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Reported theoretical FP64 peak
- 0.0708* TFLOPS
Scope and conditions
- Arithmetic density
- Not stated*
- Declared L1 cache configuration
- 128 KB (per SM)*
- Declared GPU L2 cache
- 2 MB*
- Reported display outputs
- No outputs*
- Theoretical pixel fill rate
- 56.64 GPixel/s*
- External power connectors
- None*
- Reported chip die area
- 200 mm²*
- Chip foundry
- Samsung*
- Process node declaration
- 8 nm*
- Transistors
- 8,700 million*
- Graphics processor
- GA107*
- Reported video memory
- 16* GB
- Rated memory bandwidth
- 200.1 GB/s*
- Video memory type
- GDDR6*
- Raster output units
- 32*
- Ray tracing cores
- 10*
- Reported shading units
- 1,280*
- Card or module format
- Single-slot*
- Streaming multiprocessors
- 10*
- Suggested system PSU
- 250 W*
- 2:4 tensor sparsity
- Yes*
- Declared GPU TDP
- 60 W*
- Tensor cores
- 40*
- Theoretical texture fill rate
- 70.80 GTexel/s*
- Texture mapping units
- 40*
- GPU cores
- 1,280*
- Video memory
- 16* GB
- Video memory type
- GDDR6*
Specifications 4 · 3 fields
- Device
- NVIDIA A2*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- OpenCL
- 35,467*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- Vulkan
- 34,563*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
0 selected Compare 0
* Provisional data