AI hardware
NVIDIA GeForce RTX 4080
FP16 throughput
4.9×10¹³ FLOP/s
Memory
14.9 GB
TDP
320 W
NVIDIA GeForce RTX 4080 is an AI accelerator designed by NVIDIA (GPU), released in September 2022. Its release price was $1K.
It carries 14.9 GB of memory at 668 GB/s of bandwidth. Its thermal design power is 320 W.
Full record
- Manufacturer
- NVIDIA
- Type
- GPU
- Release date
- Sep 20, 2022
- Release price
- $1K
- FP32
- 4.9×10¹³ FLOP/s
- FP64
- 7.6×10¹¹ FLOP/s
- INT8
- 3.9×10¹⁴ OP/s
- Memory
- 14.9 GB
- Memory bandwidth
- 668 GB
- TDP
- 320 W
- Transistors (millions)
- 45,900
- Die size (mm2)
- 379
- Foundry
- TSMC
- Tensor cores
- 304
More from NVIDIA
SourceEpoch AI, 'Machine Learning Hardware'. Published online at epoch.ai. Retrieved 2026-07-29 from https://epoch.ai/data/machine-learning-hardware. Licensed under CC BY 4.0.
← All ai hardware