NVIDIA RTX PRO 4000 Blackwell SFF vs Qualcomm Adreno 810 Full Specs

Summary

8,960 Shaders 1.34GHz	256 Shaders 1.05GHz
24GB GDDR7432GB/s placeholder	Shared Memory25.6GB/s LPDDR5·LPDDR4X
Peak·FP32·FP16 23.96 TFLOPS	Peak·FP32·FP16 537.6 GFLOPS
Form Factor PCIe Card	Form Factor iGPU
TDP 70W	TDP 5W

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 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Memory Bandwidth TDP

RTX PRO 4000 Blackwell SFF766.7 TFLOPSFP4 Tensor Sparse

x713.07

Adreno 8101.07 TFLOPSFP16

x1

Show Top Score

Theoretical Performance

Clock Speed1337MHz UC·Base·Boost·OC	Clock Speed1050MHz UC·Base·Boost·OC
Peak OPS 766.7 TFLOPSFP4 Tensor Sparse	Peak OPS 1.07 TFLOPSFP16
Tensor FP4 383.3 TFLOPS FP4 Tensor Sparse 766.7 TFLOPS	-
Tensor FP8-16 191.7 TFLOPS FP8-16 Tensor Sparse 383.3 TFLOPS Tensor FP8-32 95.84 TFLOPS FP8-32 Tensor Sparse 191.7 TFLOPS	-
Tensor FP16-16 95.84 TFLOPS FP16-16 Tensor Sparse 191.7 TFLOPS Tensor FP16-32 47.92 TFLOPS FP16-32 Tensor Sparse 95.84 TFLOPS	-
BF16 23.96 TFLOPS Tensor BF16 47.92 TFLOPS BF16 Tensor Sparse 95.84 TFLOPS	BF16 1.07 TFLOPS Tensor BF16 - BF16 Tensor Sparse -
Tensor TF32 23.96 TFLOPS	Tensor TF32 -
FP32 23.96 TFLOPS	FP32 537.6 GFLOPS
FP64 374.4 GFLOPS	FP64 134.4 GFLOPS
Tensor INT8 191.7 TOPS	-
Ray 72.66 TOPS	Ray -
Pixel Rate 128.4 GPixel/s	Pixel Rate 8.4 GPixel/s
Texture Rate 374.4 GTexel/s	Texture Rate 16.8 GTexel/s

Core Config

Shaders 8,960 Shaders	Shaders 256 Shaders
TMUs 280 TMUs	TMUs 16 TMUs
ROPs 96 ROPs	ROPs 8 ROPs
Tensor Cores 280 T-Cores	Tensor Cores -
RT Cores 70 RT-Cores	RT Cores -
SMs 70 SMs	EUs 2 EUs

Clocks

Base Clock 790MHz	Base Clock 895MHz
Boost Clock 1.34GHz	Boost Clock 1.05GHz

Cache

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

Memory

24GB GDDR7 placeholder	Shared Memory LPDDR5·LPDDR4X
Memory Bus 192-bit	Memory Bus 32-bit
Memory Speed 18GT/s	Memory Speed 6.4GT/s
Memory Bandwidth 432GB/s	Memory Bandwidth 25.6GB/s
ECC Yes	ECC No

Power & Thermals

TDP 70W

TDP 5W

Video Output

Max Resolution 7680x4320	Max Resolution 3840x2160
Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 165Hz	Refresh Rate Calculator 3840x2160 Resolution4K UHD Refresh Rate 60Hz
Multi-Monitor 4	Multi-Monitor 1
Adaptive Sync G-Sync FreeSync	Adaptive Sync -
DSC Supported	DSC Not Supported
HDCP HDCP 2.3	HDCP -

Ports

4x DisplayPort 2.1

-

API Support

Shader Model 6.8	Shader Model -
DirectX DirectX 12 Direct3D 12_3	DirectX DirectX 12 Direct3D 12_1
OpenGL 4.6 OpenCL 3 Vulkan 1.3	OpenGL 3.2 OpenCL 2 Vulkan 1.3
CUDA 12.8 PureVideo HD VP13 VDPAU Feature Set M	-

Encoder

Encoder 2x NVENC 9	Encoder Hexagon
Codec - - - - - AVC (H.264) HEVC (H.265) AV1	Codec H.263 MPEG-4 VC-1 VP8 VP9 AVC (H.264) HEVC (H.265) -

Decoder

Decoder 2x NVDEC 6	Decoder Hexagon AV1
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 PCIe Card	Form Factor iGPU
PCIe PCIe 5.0 x16 1-Slots	PCIe -
Height 69mm (2.72") Width 167mm (6.58") Depth 20mm (0.79")	-
Cooling Blower 1x Fan	Cooling Open-Air -

Chip

Manufacturer NVIDIA	Manufacturer Qualcomm
Chip Designer NVIDIA	Chip Designer Qualcomm
Architecture Blackwell	Architecture Adreno 800
Family RTX PRO Blackwell	Family Adreno 800
Branding	Branding
Codename NV193	Codename -
Chip Variant GB203-200-A1	Chip Variant -
Market Segment Workstation	Market Segment Smartphone
Release Date Aug 11, 2025	Release Date Oct 1, 2024

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4NP	Fabrication Node N6
Die Size 378mm²	Die Size -
Transistor Count 45.6B	Transistor Count -
Transistor Density 120.6 MTr/mm²	Transistor Density -

Images