Flop
per.io
GPU Specification Sheet
September 4, 2026
flopper.io/gpu/nvidia-geforce-rtx-2080-super-8gb
NVIDIA GeForce RTX 2080 Super 8GB
Turing
PCIe
2019
12nm
Overview
11.2
FP32 TFLOPS
8 GB
VRAM GDDR6
496 GB/s
Memory Bandwidth
250 W
TDP
Performance Metrics
Precision
Peak (dense)
Bits
Type
FP64
0.3
64
Standard
FP32
11.2
32
Standard
TF32
—
—
Standard
BF16
—
—
Standard
FP16
44.6
16
Standard
FP8
—
—
Standard
FP6
—
—
Standard
FP4
—
—
Standard
INT8
178.4
8
Standard
INT4
356.8
4
Standard
Memory Specifications
Capacity
8 GB
Type
GDDR6
Bandwidth
496 GB/s
Interface Width
256-bit
Power & Efficiency
TDP
250 W
Max Power
250 W
FP32 Efficiency
0.04 TFLOPS/W
FP16 Efficiency
0.18 TFLOPS/W
Hardware Details
Vendor:
NVIDIA
Architecture:
Turing
Process Node:
12nm
Form Factor:
PCIe
Launch Year:
2019
Variant:
8GB
Compute Engine
CUDA Cores:
3,072
Tensor Cores:
384 (Turing)
SMs:
48
Base Clock:
1.65 GHz
Boost Clock:
1.81 GHz
Interconnect
GPU-to-GPU:
NVLink
Bandwidth:
50 GB/s
Links:
1
PCIe:
3.0 x16
Chip Design
Transistors:
13.6 billion
Die Size:
545 mm²
Enterprise Features
ECC:
No
Sparsity:
No