NVIDIA B200 vs NVIDIA RTX A400 Full Specs

Summary

18,944 Shaders 1.98GHz	768 Shaders 1.76GHz
192GB HBM3e7.7TB/s	4GB GDDR696GB/s
Peak·FP32·FP16 75.02 TFLOPS	Peak·FP32·FP16 2.7 TFLOPS
Form Factor SXM6	Form Factor PCIe Card
TDP 1000W	TDP 50W

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

B20018 PFLOPSFP4 Tensor Sparse

x208.10

RTX A40086.51 TOPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1980MHz UC·Boost·OC	Clock Speed1760MHz UC·Base·Boost·OC
Peak OPS 18 PFLOPSFP4 Tensor Sparse	Peak OPS 86.51 TOPSINT4 Tensor Sparse
Tensor FP4 9 PFLOPS FP4 Tensor Sparse 18 PFLOPS	-
Tensor FP8-16 4.5 PFLOPS FP8-16 Tensor Sparse 9 PFLOPS Tensor FP8-32 4.5 PFLOPS FP8-32 Tensor Sparse 9 PFLOPS	-
Tensor FP16-16 2.25 PFLOPS FP16-16 Tensor Sparse 4.5 PFLOPS Tensor FP16-32 2.25 PFLOPS FP16-32 Tensor Sparse 4.5 PFLOPS	Tensor FP16-16 10.81 TFLOPS FP16-16 Tensor Sparse 21.63 TFLOPS Tensor FP16-32 5.41 TFLOPS FP16-32 Tensor Sparse 10.81 TFLOPS
BF16 150 TFLOPS Tensor BF16 2.25 PFLOPS BF16 Tensor Sparse 4.5 PFLOPS	BF16 2.7 TFLOPS Tensor BF16 5.41 TFLOPS BF16 Tensor Sparse 10.81 TFLOPS
Tensor TF32 1.13 PFLOPS	Tensor TF32 2.7 TFLOPS
FP32 75.02 TFLOPS	FP32 2.7 TFLOPS
FP64 37.51 TFLOPS Tensor FP64 35.16 TFLOPS	FP64 42.24 GFLOPS Tensor FP64 -
Tensor INT4 -	Tensor INT4 43.25 TOPS
Tensor INT8 4.5 POPS	Tensor INT8 21.63 TOPS
Ray -	Ray 4.08 TOPS
Pixel Rate 63.4 GPixel/s	Pixel Rate 28.2 GPixel/s
Texture Rate 1.17 TTexel/s	Texture Rate 42.2 GTexel/s

Core Config

Shaders 18,944 Shaders	Shaders 768 Shaders
TMUs 592 TMUs	TMUs 24 TMUs
ROPs 32 ROPs	ROPs 16 ROPs
Tensor Cores 592 T-Cores	Tensor Cores 24 T-Cores
RT Cores -	RT Cores 6 RT-Cores
SMs 148 SMs	SMs 6 SMs

Clocks

Base Clock -	Base Clock 1GHz
Boost Clock 1.98GHz	Boost Clock 1.76GHz
Tensor Clock 1.86GHz	Tensor Clock -

Cache

L1 64KB/SM Tex	L1 64KB/SM Tex
L2 Cache 64MB shared	L2 Cache 1MB shared

Memory

192GB HBM3e	4GB GDDR6
Memory Bus 8192-bit	Memory Bus 64-bit
Memory Speed 7.5GT/s	Memory Speed 12GT/s
Memory Bandwidth 7.7TB/s	Memory Bandwidth 96GB/s
ECC No	ECC No

Power & Thermals

TDP 1000W

TDP 50W

Video Output

Max Resolution -	Max Resolution 7680x4320
Refresh Rate Calculator -	Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz
Multi-Monitor -	Multi-Monitor 3
Adaptive Sync G-Sync FreeSync	Adaptive Sync G-Sync FreeSync
DSC Not Supported	DSC Supported
HDCP -	HDCP HDCP 2.3

Ports

-	4x Mini DisplayPort 1.4

API Support

Shader Model -	Shader Model 6.6
-	DirectX DirectX 12 Direct3D 12_2
OpenGL - OpenCL 3 Vulkan -	OpenGL 4.6 OpenCL 3 Vulkan 1.2
CUDA 10 PureVideo HD VP13 VDPAU Feature Set M	CUDA 8.6 PureVideo HD VP11 VDPAU Feature Set K

Encoder

-	Encoder NVENC 7
Codec -	Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder 7x NVDEC 6	Decoder NVDEC 5
Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1	Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) AV1

Card

Form Factor SXM6	Form Factor PCIe Card
PCIe PCIe 6.0 x16 -	PCIe PCIe 4.0 x8 1-Slots
-	Height 69mm (2.72") Width 163mm (6.42") Depth 40mm (1.57")
Cooling Passive -	Cooling Open-Air 1x Fan
Multi-GPU Multi-GPU Support Supported Multi-GPU Type NVLink	Multi-GPU -

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Blackwell	Architecture Ampere
Family Server	Family RTX A
Branding	Branding
Codename NV190	Codename NV177
Chip Variant Umbriel	Chip Variant GA107-140-A1
Market Segment Server	Market Segment Workstation
Release Date Mar 18, 2024	Release Date Apr 17, 2023

Fabrication

Foundry TSMC	Foundry Samsung
Fabrication Node 4NP	Fabrication Node 8N
Die Size 1620mm²	Die Size 200mm²
Transistor Count 208B	Transistor Count 8.7B
Transistor Density 128.4 MTr/mm²	Transistor Density 43.5 MTr/mm²

Images