NVIDIA H100 vs NVIDIA RTX PRO 6000 Blackwell Max-Q Full Specs
14,592 Shaders 1.75GHz | 24,064 Shaders 2.28GHz |
80GB HBM2e2.04TB/s | 96GB GDDR71.79TB/s |
·· 51.22 TFLOPS | ·· 109.7 TFLOPS |
Form Factor PCIe Card | Form Factor PCIe Card |
TDP 350W | TDP 300W |
Power Connectors 1x 16-Pin 12VHPWR | Power Connectors 1x 16-Pin 12VHPWR |
Clock Speed ··· | Clock Speed ·· |
Peak OPS 3.03 POPSINT8 Tensor Sparse | Peak OPS 3.51 PFLOPSFP4 Tensor Sparse |
- | Tensor FP4 1.76 PFLOPSFP4 Tensor Sparse 3.51 PFLOPS |
Tensor FP8-16 1.51 PFLOPSFP8-16 Tensor Sparse 3.03 PFLOPSTensor FP8-32 1.51 PFLOPSFP8-32 Tensor Sparse 3.03 PFLOPS | Tensor FP8-16 877.9 TFLOPSFP8-16 Tensor Sparse 1.76 PFLOPSTensor FP8-32 438.9 TFLOPSFP8-32 Tensor Sparse 877.9 TFLOPS |
Tensor FP16-16 756.4 TFLOPSFP16-16 Tensor Sparse 1.51 PFLOPSTensor FP16-32 756.4 TFLOPSFP16-32 Tensor Sparse 1.51 PFLOPS | Tensor FP16-16 438.9 TFLOPSFP16-16 Tensor Sparse 877.9 TFLOPSTensor FP16-32 219.5 TFLOPSFP16-32 Tensor Sparse 438.9 TFLOPS |
BF16 102.4 TFLOPSTensor BF16 756.4 TFLOPSBF16 Tensor Sparse 1.51 PFLOPS | BF16 109.7 TFLOPSTensor BF16 219.5 TFLOPSBF16 Tensor Sparse 438.9 TFLOPS |
Tensor TF32 378.2 TFLOPS | Tensor TF32 109.7 TFLOPS |
FP32 51.22 TFLOPS | FP32 109.7 TFLOPS |
FP64 25.61 TFLOPSTensor FP64 47.28 TFLOPS | FP64 1.72 TFLOPSTensor FP64 - |
Tensor INT8 1.51 POPS | Tensor INT8 877.9 TOPS |
Ray - | Ray 332.8 TOPS |
Pixel Rate 42.1 GPixel/s | Pixel Rate 437.8 GPixel/s |
Texture Rate 800.3 GTexel/s | Texture Rate 1.72 TTexel/s |
Shaders 14,592 Shaders | Shaders 24,064 Shaders |
TMUs 456 TMUs | TMUs 752 TMUs |
ROPs 24 ROPs | ROPs 192 ROPs |
Tensor Cores 456 T-Cores | Tensor Cores 752 T-Cores |
RT Cores - | RT Cores 188 RT-Cores |
SMs 114 SMs | SMs 188 SMs |
Base Clock 1.06GHz | Base Clock - |
Boost Clock 1.75GHz | Boost Clock 2.28GHz |
Tensor Clock 1.62GHz | Tensor Clock - |
L2 Cache 51.2MB shared | L2 Cache 131.1MB shared |
80GB HBM2e | 96GB GDDR7 |
Memory Bus 5120-bit | Memory Bus 512-bit |
Memory Speed 3.2GT/s | Memory Speed 28GT/s |
Memory Bandwidth 2.04TB/s | Memory Bandwidth 1.79TB/s |
ECC - | ECC Yes |
TDP 350W | TDP 300W |
Multi-Monitor - | Multi-Monitor 4 |
HDCP - | HDCP HDCP 2.3 |
- | 4x DisplayPort 2.1 |
- | Encoder Model 4x NVENC 9 |
Decoder Model 7x NVDEC 5 | Decoder Model 4x NVDEC 6 |
Form Factor PCIe Card | Form Factor PCIe Card |
PCIe 2-Slots | PCIe 2-Slots |
Height 111 mm (4.37")Width 268 mm (10.55")Depth 40 mm (1.57") | Height 111.8 mm (4.4")Width 304 mm (11.97")Depth 40 mm (1.57") |
Cooling Passive - | Cooling Blower 1x Fan |
Power Connectors 1x 16-Pin 12VHPWR | Power Connectors 1x 16-Pin 12VHPWR |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding ![]() | Branding ![]() |
Codename NV180 | Codename NV192 |
Chip Variant - | Chip Variant GB202-250-A1 |
Market Segment Server | Market Segment Workstation |
Release Date Mar 22, 2022 | Release Date Mar 18, 2025 |
Foundry TSMC | Foundry TSMC |
Fabrication Node 4N | Fabrication Node 4NP |
Die Size 814mm² | Die Size 762mm² |
Transistor Count 80 Billion | Transistor Count 92.2 Billion |
Transistor Density 98.28 MTr/mm² | Transistor Density 121.1 MTr/mm² |
No images available
No images available



