NVIDIA A10 vs NVIDIA A16 Full Specs

Summary

9,216 Shaders 1.7GHz	5,120 Shaders 1.7GHz
24GB GDDR6300.3GB/s	64GB GDDR6463.4GB/s
Peak·FP32·FP16 31.24 TFLOPS	Peak·FP32·FP16 17.36 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 150W	TDP 250W
Power Connectors 1x 8-Pin -	Power Connectors - 1x 8-Pin EPS

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

A10999.8 TOPSINT4 Tensor Sparse

x1.80

A16555.4 TOPSINT4 Tensor Sparse (4x 138.9 TOPS)

x1

Show Top Score

Theoretical Performance

Clock Speed1695MHz UC·Base·Boost·OC	Clock Speed1695MHz UC·Base·Boost·OC
Peak OPS 999.8 TOPSINT4 Tensor Sparse	Peak OPS 555.4 TOPSINT4 Tensor Sparse
Tensor FP16-16 125 TFLOPS FP16-16 Tensor Sparse 249.9 TFLOPS Tensor FP16-32 62.48 TFLOPS FP16-32 Tensor Sparse 125 TFLOPS	Tensor FP16-16 69.43 TFLOPS FP16-16 Tensor Sparse 138.9 TFLOPS Tensor FP16-32 34.71 TFLOPS FP16-32 Tensor Sparse 69.43 TFLOPS
BF16 31.24 TFLOPS Tensor BF16 62.48 TFLOPS BF16 Tensor Sparse 125 TFLOPS	BF16 17.36 TFLOPS Tensor BF16 34.71 TFLOPS BF16 Tensor Sparse 69.43 TFLOPS
Tensor TF32 31.24 TFLOPS	Tensor TF32 17.36 TFLOPS
FP32 31.24 TFLOPS	FP32 17.36 TFLOPS
FP64 488.2 GFLOPS	FP64 271.2 GFLOPS
Tensor INT4 499.9 TOPS	Tensor INT4 277.7 TOPS
Tensor INT8 249.9 TOPS	Tensor INT8 138.9 TOPS
Ray 47.12 TOPS	Ray 26.18 TOPS
Pixel Rate 162.7 GPixel/s	Pixel Rate 54.2 GPixel/s
Texture Rate 488.2 GTexel/s	Texture Rate 67.8 GTexel/s

Core Config

Shaders 9,216 Shaders	Shaders 5,120 Shaders
TMUs 288 TMUs	TMUs 160 TMUs
ROPs 96 ROPs	ROPs 128 ROPs
Tensor Cores 288 T-Cores	Tensor Cores 160 T-Cores
RT Cores 72 RT-Cores	RT Cores 40 RT-Cores
SMs 72 SMs	SMs 40 SMs

Clocks

Base Clock 885MHz	Base Clock 885MHz
Boost Clock 1.7GHz	Boost Clock 1.7GHz

Cache

L2 Cache 6.1MB shared

L2 Cache 2MB shared

Memory

24GB GDDR6	64GB GDDR6
Memory Bus 384-bit	Memory Bus 128-bit
Memory Speed 6.3GT/s	Memory Speed 7.2GT/s
Memory Bandwidth 300.3GB/s	Memory Bandwidth 463.4GB/s

Power & Thermals

TDP 150W

TDP 250W

Encoder

Encoder Model NVENC 7

Encoder Model NVENC 7

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 1-Slots	PCIe 2-Slots
Height 112 mm (4.41") Width 267 mm (10.51") Depth 20 mm (0.79")	Height 112 mm (4.41") Width 267 mm (10.51") Depth 40 mm (1.57")
Cooling Passive	Cooling Passive
Power Connectors 1x 8-Pin	Power Connectors 1x 8-Pin EPS

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ampere	Architecture Ampere
Family Server	Family Server
Branding	Branding
Codename NV172	Codename NV177
Chip Variant GA102-200-KD-A1	Chip Variant GA107-140-A1
Market Segment Server	Market Segment Server
Release Date Apr 12, 2021	Release Date Apr 12, 2021

Fabrication

Foundry Samsung	Foundry Samsung
Fabrication Node 8N	Fabrication Node 8N
Die Size 628mm²	Die Size 200mm²
Transistor Count 28.3 Billion	Transistor Count 8.7 Billion
Transistor Density 45.04 MTr/mm²	Transistor Density 43.5 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAA10 vs GPU NVIDIARTX 4000 Ada NVIDIAA10 vs GPU NVIDIARTX 4500 Ada NVIDIAA10 vs GPU AMDRadeon RX 9060 XT 16GB Show 12 more

NVIDIAA16 vs GPU AMDRadeon RX 9060 XT 16GB NVIDIAA16 vs GPU AMDRadeon RX 7600 XT NVIDIAA16 vs GPU AMDRadeon RX 9070 Show 12 more