NVIDIA RTX 2000 Max-Q Full Specs
3,072 Shaders 1.46GHz |
8GB GDDR6256GB/s |
·· 8.94 TFLOPS |
Form Factor Soldered |
TDP 50W |
Clock Speed ··· |
Peak OPS 286.1 TOPSINT4 Tensor Sparse |
Tensor FP8-16 71.52 TFLOPSFP8-16 Tensor Sparse 143 TFLOPSTensor FP8-32 35.76 TFLOPSFP8-32 Tensor Sparse 71.52 TFLOPS |
Tensor FP16-16 35.76 TFLOPSFP16-16 Tensor Sparse 71.52 TFLOPSTensor FP16-32 17.88 TFLOPSFP16-32 Tensor Sparse 35.76 TFLOPS |
BF16 8.94 TFLOPSTensor BF16 17.88 TFLOPSBF16 Tensor Sparse 35.76 TFLOPS |
Tensor TF32 8.94 TFLOPS |
FP32 8.94 TFLOPS |
FP64 139.7 GFLOPS |
Tensor INT4 143 TOPS |
Tensor INT8 71.52 TOPS |
Ray 20.66 TOPS |
Pixel Rate 69.8 GPixel/s |
Texture Rate 139.7 GTexel/s |
Shaders 3,072 Shaders |
TMUs 96 TMUs |
ROPs 48 ROPs |
Tensor Cores 96 T-Cores |
RT Cores 24 RT-Cores |
SMs 24 SMs |
Base Clock 930MHz |
Boost Clock 1.46GHz |
L2 Cache 12.3MB shared |
8GB GDDR6 |
Memory Bus 128-bit |
Memory Speed 16GT/s |
Memory Bandwidth 256GB/s |
TDP 50W |
Multi-Monitor 4 |
HDCP HDCP 2.3 |
Encoder Model NVENC 8 |
Decoder Model NVDEC 5 |
Form Factor Soldered |
Manufacturer |
Chip Designer |
Architecture |
Family |
Branding  |
Codename NV187 |
Chip Variant AD107 |
Market Segment Laptop |
Release Date Mar 21, 2023 |
Foundry TSMC |
Fabrication Node 4N |
Die Size 159mm² |
Transistor Count 18.9 Billion |
Transistor Density 118.9 MTr/mm² |
No images available
