NVIDIA B200 vs NVIDIA RTX 4000 Ada Full Specs - HMC

18,944 Shaders 1.98GHz	6,144 Shaders 2.17GHz
192GB HBM3e7.7TB/s	20GB GDDR6280GB/s
·· 75.02 TFLOPS	·· 26.73 TFLOPS
Form Factor SXM6	Form Factor PCIe Card
TDP 1000W	TDP 130W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

B200

B20018 PFLOPSFP4 Tensor Sparse

x21.05

RTX 4000 Ada

RTX 4000 Ada855.2 TOPSINT4 Tensor Sparse

x1

Clock Speed ··	Clock Speed ···
Peak OPS 18 PFLOPSFP4 Tensor Sparse	Peak OPS 855.2 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 FP8-16 213.8 TFLOPS FP8-16 Tensor Sparse 427.6 TFLOPS Tensor FP8-32 106.9 TFLOPS FP8-32 Tensor Sparse 213.8 TFLOPS
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 FP16-16 106.9 TFLOPS FP16-16 Tensor Sparse 213.8 TFLOPS Tensor FP16-32 53.45 TFLOPS FP16-32 Tensor Sparse 106.9 TFLOPS
BF16 150 TFLOPS Tensor BF16 2.25 PFLOPS BF16 Tensor Sparse 4.5 PFLOPS	BF16 26.73 TFLOPS Tensor BF16 53.45 TFLOPS BF16 Tensor Sparse 106.9 TFLOPS
Tensor TF32 1.13 PFLOPS	Tensor TF32 26.73 TFLOPS
FP32 75.02 TFLOPS	FP32 26.73 TFLOPS
FP64 37.51 TFLOPS Tensor FP64 35.16 TFLOPS	FP64 417.6 GFLOPS Tensor FP64 -
Tensor INT4 -	Tensor INT4 427.6 TOPS
Tensor INT8 4.5 POPS	Tensor INT8 213.8 TOPS
Ray -	Ray 61.78 TOPS
Pixel Rate 63.4 GPixel/s	Pixel Rate 174 GPixel/s
Texture Rate 1.17 TTexel/s	Texture Rate 417.6 GTexel/s

Shaders 18,944 Shaders	Shaders 6,144 Shaders
TMUs 592 TMUs	TMUs 192 TMUs
ROPs 32 ROPs	ROPs 80 ROPs
Tensor Cores 592 T-Cores	Tensor Cores 192 T-Cores
RT Cores -	RT Cores 48 RT-Cores
SMs 148 SMs	SMs 48 SMs

Base Clock -	Base Clock 1.5GHz
Boost Clock 1.98GHz	Boost Clock 2.17GHz
Tensor Clock 1.86GHz	Tensor Clock -

L1 64KB/SM Tex	L1 64KB/SM Tex
L2 Cache 64MB shared	L2 Cache 48MB shared

192GB HBM3e	20GB GDDR6
Memory Bus 8192-bit	Memory Bus 160-bit
Memory Speed 7.5GT/s	Memory Speed 14GT/s
Memory Bandwidth 7.7TB/s	Memory Bandwidth 280GB/s
ECC No	ECC Yes

TDP

1000W

TDP

130W

Max Resolution -	Max Resolution 7680x4320
Refresh Rate Calculator -	Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 60Hz
Multi-Monitor -	Multi-Monitor 4
Adaptive Sync G-Sync FreeSync	Adaptive Sync G-Sync FreeSync
DSC Not Supported	DSC Supported
HDCP -	HDCP HDCP 2.3

-	4x Mini DisplayPort 1.4

Shader Model -	Shader Model 6.7
-	DirectX DirectX 12 Direct3D 12_3
OpenGL - OpenCL 3 Vulkan -	OpenGL 4.6 OpenCL 3 Vulkan 1.3
CUDA 10 PureVideo HD VP13 VDPAU Feature Set M	CUDA 8.9 PureVideo HD VP12 VDPAU Feature Set L

-	Encoder 2x NVENC 8
Codec -	Codec AVC (H.264) HEVC (H.265) AV1

Decoder 7x NVDEC 6	Decoder 2x 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

Form Factor SXM6	Form Factor PCIe Card
PCIe PCIe 6.0 x16 -	PCIe PCIe 4.0 x16 1-Slots
-	Height 112mm (4.41") Width 245mm (9.65") Depth 20mm (0.79")
Cooling Passive	Cooling Passive
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR
Multi-GPU Multi-GPU Support Supported Multi-GPU Type NVLink	Multi-GPU -

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Blackwell	Architecture Ada Lovelace
Family Server	Family RTX Ada
Branding	Branding
Codename NV190	Codename NV184
Chip Variant Umbriel	Chip Variant AD104-250
Market Segment Server	Market Segment Workstation
Release Date Mar 18, 2024	Release Date Aug 9, 2023

Foundry TSMC	Foundry TSMC
Fabrication Node 4NP	Fabrication Node 4N
Die Size 1620mm²	Die Size 295mm²
Transistor Count 208B	Transistor Count 35.8B
Transistor Density 128.4 MTr/mm²	Transistor Density 121.6 MTr/mm²