NVIDIA B200 vs NVIDIA GeForce RTX 5090 Laptop 95W Full Specs
18,944 Shaders 1.98GHz | 10,496 Shaders 1.6GHz |
192GB HBM3e7.7TB/s | 24GB GDDR7896GB/s |
·· 75.02 TFLOPS | ·· 33.52 TFLOPS |
Form Factor SXM6 | Form Factor Soldered |
TDP 1000W | TDP 95W |
Clock Speed ·· | Clock Speed ··· |
Peak OPS 18 PFLOPSFP4 Tensor Sparse | Peak OPS 1.42 PFLOPSFP4 Tensor Sparse |
Tensor FP4 9 PFLOPSFP4 Tensor Sparse 18 PFLOPS | Tensor FP4 710.4 TFLOPSFP4 Tensor Sparse 1.42 PFLOPS |
Tensor FP8-16 4.5 PFLOPSFP8-16 Tensor Sparse 9 PFLOPSTensor FP8-32 4.5 PFLOPSFP8-32 Tensor Sparse 9 PFLOPS | Tensor FP8-16 355.2 TFLOPSFP8-16 Tensor Sparse 710.4 TFLOPSTensor FP8-32 177.6 TFLOPSFP8-32 Tensor Sparse 355.2 TFLOPS |
Tensor FP16-16 2.25 PFLOPSFP16-16 Tensor Sparse 4.5 PFLOPSTensor FP16-32 2.25 PFLOPSFP16-32 Tensor Sparse 4.5 PFLOPS | Tensor FP16-16 177.6 TFLOPSFP16-16 Tensor Sparse 355.2 TFLOPSTensor FP16-32 88.8 TFLOPSFP16-32 Tensor Sparse 177.6 TFLOPS |
BF16 150 TFLOPSTensor BF16 2.25 PFLOPSBF16 Tensor Sparse 4.5 PFLOPS | BF16 33.52 TFLOPSTensor BF16 88.8 TFLOPSBF16 Tensor Sparse 177.6 TFLOPS |
Tensor TF32 1.13 PFLOPS | Tensor TF32 44.4 TFLOPS |
FP32 75.02 TFLOPS | FP32 33.52 TFLOPS |
FP64 37.51 TFLOPSTensor FP64 35.16 TFLOPS | FP64 523.8 GFLOPSTensor FP64 - |
Tensor INT8 4.5 POPS | Tensor INT8 355.2 TOPS |
Ray - | Ray 101.7 TOPS |
Pixel Rate 63.4 GPixel/s | Pixel Rate 178.9 GPixel/s |
Texture Rate 1.17 TTexel/s | Texture Rate 523.8 GTexel/s |
Shaders 18,944 Shaders | Shaders 10,496 Shaders |
TMUs 592 TMUs | TMUs 328 TMUs |
ROPs 32 ROPs | ROPs 112 ROPs |
Tensor Cores 592 T-Cores | Tensor Cores 328 T-Cores |
RT Cores - | RT Cores 82 RT-Cores |
SMs 148 SMs | SMs 82 SMs |
Base Clock - | Base Clock 930MHz |
Boost Clock 1.98GHz | Boost Clock 1.6GHz |
Tensor Clock 1.86GHz | Tensor Clock 2.12GHz |
L1 64KB/SM Tex | L1 64KB/SM Tex |
L2 Cache 64MB shared | L2 Cache 64MB shared |
192GB HBM3e | 24GB GDDR7 |
Memory Bus 8192-bit | Memory Bus 256-bit |
Memory Speed 7.5GT/s | Memory Speed 28GT/s |
Memory Bandwidth 7.7TB/s | Memory Bandwidth 896GB/s |
ECC No | ECC No |
TDP 1000W | TDP 95W |
Max Resolution - | Max Resolution 7680x4320 |
Refresh Rate Calculator - | Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 165Hz |
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 |
Shader Model - | Shader Model 6.8 |
- | DirectX DirectX 12Direct3D 12_3 |
OpenGL -OpenCL 3Vulkan - | OpenGL 4.6OpenCL 3Vulkan 1.3 |
CUDA 10PureVideo HD VP13VDPAU Feature Set M | CUDA 12.8PureVideo HD VP13VDPAU Feature Set M |
- | Encoder 3x NVENC 9 |
Codec - | Codec AVC (H.264) HEVC (H.265) AV1 |
Decoder 7x NVDEC 6 | Decoder 2x NVDEC 6 |
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 Soldered |
PCIe PCIe 6.0 x16 | PCIe PCIe 5.0 x16 |
Cooling Passive | Cooling Open-Air |
Multi-GPU Multi-GPU Support SupportedMulti-GPU Type NVLink | Multi-GPU - |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding ![]() | Branding ![]() |
Codename NV190 | Codename NV193 |
Chip Variant Umbriel | Chip Variant GB203-200-A1 |
Market Segment Server | Market Segment Laptop |
Release Date Mar 18, 2024 | Release Date Jan 6, 2025 |
Foundry TSMC | Foundry TSMC |
Fabrication Node 4NP | Fabrication Node 4NP |
Die Size 1620mm² | Die Size 378mm² |
Transistor Count 208B | Transistor Count 45.6B |
Transistor Density 128.4 MTr/mm² | Transistor Density 120.6 MTr/mm² |





