NVIDIA Tesla M6 vs NVIDIA A16 Full Specs

Summary

1,536 Shaders 1.05GHz	5,120 Shaders 1.7GHz
8GB GDDR5147.2GB/s	64GB GDDR6463.4GB/s
Peak·FP32·FP16 3.23 TFLOPS	Peak·FP32·FP16 17.36 TFLOPS
Form Factor MXM-A	Form Factor PCIe Card
TDP 100W	TDP 250W
Power Connectors -	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

Tesla M63.23 TFLOPSFP32

x1

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

x172.03

Show Top Score

Theoretical Performance

Clock Speed1051MHz UC·Base·Boost·OC	Clock Speed1695MHz UC·Base·Boost·OC
Peak OPS 3.23 TFLOPSFP32	Peak OPS 555.4 TOPSINT4 Tensor Sparse
-	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 17.36 TFLOPS Tensor BF16 34.71 TFLOPS BF16 Tensor Sparse 69.43 TFLOPS
Tensor TF32 -	Tensor TF32 17.36 TFLOPS
FP32 3.23 TFLOPS	FP32 17.36 TFLOPS
FP64 100.9 GFLOPS	FP64 271.2 GFLOPS
Tensor INT4 -	Tensor INT4 277.7 TOPS
-	Tensor INT8 138.9 TOPS
Ray -	Ray 26.18 TOPS
Pixel Rate 67.3 GPixel/s	Pixel Rate 54.2 GPixel/s
Texture Rate 100.9 GTexel/s	Texture Rate 67.8 GTexel/s

Core Config

Shaders 1,536 Shaders	Shaders 5,120 Shaders
TMUs 96 TMUs	TMUs 160 TMUs
ROPs 64 ROPs	ROPs 128 ROPs
Tensor Cores -	Tensor Cores 160 T-Cores
RT Cores -	RT Cores 40 RT-Cores
SMs 12 SMs	SMs 40 SMs

Clocks

Base Clock 722MHz	Base Clock 885MHz
Boost Clock 1.05GHz	Boost Clock 1.7GHz

Cache

L2 Cache 2MB shared

L2 Cache 2MB shared

Memory

8GB GDDR5	64GB GDDR6
Memory Bus 256-bit	Memory Bus 128-bit
Memory Speed 4.6GT/s	Memory Speed 7.2GT/s
Memory Bandwidth 147.2GB/s	Memory Bandwidth 463.4GB/s

Power & Thermals

TDP 100W

TDP 250W

Encoder

Encoder Model 2x NVENC 3

Encoder Model NVENC 7

Decoder

Decoder Model NVDEC 1

Decoder Model NVDEC 5

Card

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

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Maxwell 2	Architecture Ampere
Family Tesla M	Family Server
Branding	Branding
Codename NV124	Codename NV177
Chip Variant -	Chip Variant GA107-140-A1
Market Segment Server	Market Segment Server
Release Date Aug 30, 2015	Release Date Apr 12, 2021

Fabrication

Foundry TSMC	Foundry Samsung
Fabrication Node 28nm	Fabrication Node 8N
Die Size 398mm²	Die Size 200mm²
Transistor Count 5.2 Billion	Transistor Count 8.7 Billion
Transistor Density 13.07 MTr/mm²	Transistor Density 43.5 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIATesla M6 vs GPU AMDRadeon RX 7400 NVIDIATesla M6 vs GPU AMDRadeon PRO W7400 NVIDIATesla M6 vs GPU AMDRadeon PRO W7500 Show 8 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