NVIDIA GeForce RTX 3090
Consumer
VRAM
24 GB
Memory
GDDR6X
Bandwidth
936 GB/s
TDP
350W
Suitable Workloads
Smaller Language Models
Inference for 7B-13B parameter models
Key Highlights
- Built on Ampere architecture
- 10,496 compute cores for parallel processing
- PCIe form factor
Memory
VRAM24 GB
Memory TypeGDDR6X
Memory Bandwidth936 GB/s
Compute Performance
FP32 (Single Precision)35.6 TFLOPS
FP16 (Half Precision)142 TFLOPS
BF16142 TFLOPS
Architecture
ArchitectureAmpere
Compute Cores10,496
Release Year2020
Power & Physical
TDP350 W
Form FactorPCIe
PCIe GenerationPCIe 4.0
Notes
FP16 dense tensor with FP16 accumulate. Budget 24GB self-host option on the used market.
Models That May Fit on NVIDIA GeForce RTX 3090
Estimates based on INT8 quantization. Actual fit depends on framework and batch size.
Explore More
Added Jul 30, 2026
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.