NVIDIA Ampere
NVIDIA RTX 3090 Ti
RTX 3090 Ti squeezes extra performance out of Ampere for demanding ML training workloads.
- Launch year
- 2022
- Memory
- 24 GB GDDR6X
- Memory bandwidth
- 1.0 TB/s
- Peak FP16 / FP32
- 90 TFLOPS · 45 TFLOPS
Market snapshot
No live pricing
Awaiting availability from providers.
Catalog coverage
0 live offerings
Across 0 providers · 0 regions
- Highest Ampere clocks
- 24 GB VRAM
- Excellent diffusion timings
Last refreshed Oct 20, 2025, 1:51 AM
Performance snapshot
Normalized versus NVIDIA A100 (=1.0). Values use public reference benchmarks for training and inference workloads.
- AI Training×0.75
- Diffusion×0.85
- Memory Bandwidth×0.48
No offerings found for this model.