GeekRadar / The comparison desk
COMPARE.
GPUA10
Graphics processor
- Video memory
- 24 GB*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 600 GB/s*
Benchmark results
- Geekbench GPU (reported compilation) · version unreported · CUDA186,108*Platform unreported Compare results
- Geekbench GPU (reported compilation) · version unreported · CUDA186,108*Platform unreported Compare results
Processing & platform
- Architecture
- Ampere*
Memory & storage
- Video memory
- 24 GB*
- Video memory type
- GDDR6*
- Memory bus
- 384 bit*
- Rated memory bandwidth
- 600 GB/s*
System configuration
Detailed specifications
Specifications 1 · 19 fields
- GPU architecture — NVIDIA A10 — 24 GB GDDR6
- Ampere*
- Theoretical peak: BF16 tensor dense per GPU — NVIDIA A10 — 24 GB GDDR6
- 125* TFLOPS
- Theoretical peak: FP16 tensor dense per GPU — NVIDIA A10 — 24 GB GDDR6
- 125* TFLOPS
- Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA A10 — 24 GB GDDR6
- 31.2* TFLOPS
- Native hardware support: FP4 tensor — NVIDIA A10 — 24 GB GDDR6
- No*
- Native hardware support: FP64 tensor — NVIDIA A10 — 24 GB GDDR6
- No*
- Native hardware support: FP6 tensor — NVIDIA A10 — 24 GB GDDR6
- No*
- Native hardware support: FP8 tensor — NVIDIA A10 — 24 GB GDDR6
- No*
- Theoretical peak: INT8 tensor dense per GPU — NVIDIA A10 — 24 GB GDDR6
- 250* TOPS
- Theoretical peak: TF32 tensor dense per GPU — NVIDIA A10 — 24 GB GDDR6
- 62.5* TFLOPS
- Physical configuration — NVIDIA A10 — 24 GB GDDR6
- PCIe, single-slot FHFL*
- Native hardware support for GPU interconnect — NVIDIA A10 — 24 GB GDDR6
- No*
- PCIe interface declaration — NVIDIA A10 — 24 GB GDDR6
- PCIe Gen4 x16*
- Maximum board power — NVIDIA A10 — 24 GB GDDR6
- 150* W
- Peak memory bandwidth per GPU — NVIDIA A10 — 24 GB GDDR6
- 600* GB/s
- Memory interface width per GPU — NVIDIA A10 — 24 GB GDDR6
- 384* bit
- Memory capacity per GPU — NVIDIA A10 — 24 GB GDDR6
- 24* GB
- Memory technology — NVIDIA A10 — 24 GB GDDR6
- GDDR6*
- GPU model — NVIDIA A10 — 24 GB GDDR6
- NVIDIA A10*
Specifications 2 · 3 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
- A10*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- CUDA
- 186,108*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
Specifications 3 · 3 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
- A10*
Scope and conditions
- benchmark_context
- suite
- Geekbench GPU (reported compilation)*
- backend_columns
- CUDA*
- Metal*
- OpenCL*
- Vulkan*
- test_configuration_verified
- No*
- comparable
- No*
- CUDA
- 186,108*
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