NVIDIA · Ada Lovelace · 2022
NVIDIA RTX 4080. Not in stock right now.
16 GB of GDDR6X and 97.5 TFLOPS FP16 non-tensor, for training and inference. The RTX 4090 is on demand now from $0.58/hr per GPU on an 8-GPU machine.
Not in stock right now
RTX 4080 is not in stock right now.
Leave your work email to register interest. These requests decide which GPUs we bring on demand next.
The card
16 GB of GDDR6X. At 736 GB/s.
- Memory
- 16 GB
- GDDR6X
- Bandwidth
- 736 GB/s
- Memory to compute
- FP16
- 97.5
- non-tensor TFLOPS
- Per node
- 2 GPUs
- PCIe, 320 W each
Spec sheet
How the RTX 4080 compares. Against its closest alternatives.
Alternatives
Alternatives to the RTX 4080. Same account, different price and performance.
| GPU | Memory · FP16 non-tensor | Stands out | Price gap | From |
|---|---|---|---|---|
| NVIDIA RTX 4080This GPU | 16 GB GDDR6X · 97.5 TFLOPS | Not in stock right now | ||
| NVIDIA RTX 4070 Ti | 12 GB GDDR6X · 80.2 TFLOPS | -4 GB memory | Not in stock right now | |
| NVIDIA RTX 3090 | 24 GB GDDR6X · 71 TFLOPS | +8 GB memory | $0.41/hr | |
| NVIDIA V100 | 32 GB HBM2 | +16 GB memory | $3.35/hr | |
| NVIDIA A40 | 48 GB GDDR6 | +32 GB memory | $2.66/hr |
Full specs
NVIDIA RTX 4080 specifications.
Memory
- Memory
- 16 GB
- Type
- GDDR6X
- Bandwidth
- 736 GB/s
Compute
- FP32
- 48.7 TFLOPS
- FP16 non-tensor
- 97.5 TFLOPS
- INT8
- 390 TOPS
- CUDA cores
- 9,728
Power and form
- TDP
- 320 W
- Form factor
- Consumer
- Architecture
- Ada Lovelace
- Released
- 2022
Node
- GPUs per node
- 2
- Interconnect
- PCIe
- Maker
- NVIDIA
Questions
Renting the RTX 4080. What buyers ask first.
Other GPUs
Browse every GPU by architecture.
NVIDIA Blackwell
NVIDIA Hopper
NVIDIA Ampere
NVIDIA Ada Lovelace
NVIDIA Volta