NVIDIA A16 Full Specs
5,120 Shaders 1.7GHz |
64GB GDDR6463.4GB/s |
·· 17.36 TFLOPS |
Form Factor PCIe Card |
TDP 250W |
Power Connectors 1x 8-Pin EPS |
Clock Speed ··· |
Peak OPS 555.4 TOPSINT4 Tensor Sparse |
Tensor FP16-16 69.43 TFLOPSFP16-16 Tensor Sparse 138.9 TFLOPSTensor FP16-32 34.71 TFLOPSFP16-32 Tensor Sparse 69.43 TFLOPS |
BF16 17.36 TFLOPSTensor BF16 34.71 TFLOPSBF16 Tensor Sparse 69.43 TFLOPS |
Tensor TF32 17.36 TFLOPS |
FP32 17.36 TFLOPS |
FP64 271.2 GFLOPS |
Tensor INT4 277.7 TOPS |
Tensor INT8 138.9 TOPS |
Ray 26.18 TOPS |
Pixel Rate 54.2 GPixel/s |
Texture Rate 67.8 GTexel/s |
Shaders 5,120 Shaders |
TMUs 160 TMUs |
ROPs 128 ROPs |
Tensor Cores 160 T-Cores |
RT Cores 40 RT-Cores |
SMs 40 SMs |
Base Clock 885MHz |
Boost Clock 1.7GHz |
L2 Cache 2MB shared |
64GB GDDR6 |
Memory Bus 128-bit |
Memory Speed 7.2GT/s |
Memory Bandwidth 463.4GB/s |
ECC No |
TDP 250W |
Encoder Model NVENC 7 |
Codec AVC (H.264) HEVC (H.265) |
Decoder Model NVDEC 5 |
Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1 |
Form Factor PCIe Card |
PCIe 2-Slots |
Height 112 mm (4.41")Width 267 mm (10.51")Depth 40 mm (1.57") |
Cooling Passive |
Power Connectors 1x 8-Pin EPS |
Foundry Samsung |
Fabrication Node 8N |
Die Size 200mm² |
Transistor Count 8.7 Billion |
Transistor Density 43.5 MTr/mm² |
