Specifications Compared
| Spec | RTX 2080 Ti | RTX 3090 |
|---|---|---|
| TDP | 215W | 350W |
| VRAM | 11 GB | 24 GB |
| CUDA Cores | 2,944 | 10,496 |
| Memory Type | GDDR6 | GDDR6X |
| Architecture | Turing | Ampere |
| FP16 (dense) | 40.3 TFLOPS | 71 TFLOPS |
| Form Factors | PCIe | PCIe |
| INT8 (dense) | 161.1 TOPS | 284 TOPS |
| Interconnect | NVLink, PCIe 3.0 | NVLink, PCIe 4.0 |
| Tensor Cores | 368 | 328 |
| FP32 Performance | 10 TFLOPS | 35.6 TFLOPS |
| Memory Bandwidth | 448 GB/s | 936 GB/s |
| FP16 (with sparsity) | Not published | 142 TFLOPS |
| INT8 (with sparsity) | Not published | 568 TOPS |
Performance Analysis
The RTX 2080 Ti delivers 40.3 TFLOPS dense FP16 and 10 TFLOPS FP32 while the RTX 3090 delivers 71 TFLOPS dense FP16 and 35.6 TFLOPS FP32. This dense FP16 ratio of roughly 1 to 1.76 indicates the RTX 3090 processes larger batches during inference or training steps that rely on dense tensor operations. Memory bandwidth of 448 GB/s on the RTX 2080 Ti versus 936 GB/s on the RTX 3090 allows the RTX 3090 to sustain larger batch sizes before memory becomes the limiting factor. Both GPUs report dense INT8 figures of 161.1 TOPS and 284 TOPS respectively so comparisons must remain within the dense category without mixing sparsity values.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
RTX 2080 Ti
RTX 2080 Ti is not offered on-demand by any provider we track right now. See the RTX 2080 Ti rental page for last-seen listed prices and a price alert.
Notify me when RTX 2080 Ti drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold.
QuantaCloud
Comparing providers? We broker across all of them.
Stop tab-switching between pricing pages. Tell us what you need, 16+ GPUs reserved or cluster capacity, and we return one quote at partner rates within 24 hours.
When to Choose the RTX 2080 Ti
The RTX 2080 Ti variant suits workloads where the 215 W TDP keeps total system power under strict limits. Its 11 GB GDDR6 capacity combined with 448 GB/s bandwidth supports smaller models that fit within that memory envelope without requiring the higher 350 W TDP of the alternative.
When to Choose the RTX 3090
The RTX 3090 variant fits workloads that need the 24 GB GDDR6X capacity and 936 GB/s bandwidth to hold larger tensors. Its 71 TFLOPS dense FP16 and 35.6 TFLOPS FP32 enable faster iteration on tasks that scale with those dense figures compared with the 40.3 TFLOPS dense FP16 and 10 TFLOPS FP32 of the other variant.
Use Cases
The 24 GB capacity exceeds the 11 GB limit while the 35.6 TFLOPS FP32 figure supports larger training batches than the 10 TFLOPS FP32 alternative.
Dense FP16 throughput reaches 71 TFLOPS against 40.3 TFLOPS and the 936 GB/s bandwidth sustains higher token rates than 448 GB/s.
The 24 GB GDDR6X memory accommodates adapter layers that exceed 11 GB while dense INT8 performance of 284 TOPS exceeds 161.1 TOPS.
The 24 GB capacity holds larger diffusion models and the 936 GB/s bandwidth reduces latency compared with the 448 GB/s figure.
Both variants share NVLink interconnect and the FP32 figures of 10 TFLOPS and 35.6 TFLOPS allow selection based on exact memory needs.
Frequently Asked Questions
What memory capacities distinguish the two variants?▾
The RTX 2080 Ti variant holds 11 GB GDDR6 while the RTX 3090 variant holds 24 GB GDDR6X. These capacities determine the largest model that fits without offloading.
How do the FP32 figures compare for general compute?▾
The RTX 2080 Ti provides 10 TFLOPS FP32 and the RTX 3090 provides 35.6 TFLOPS FP32. The difference scales directly with throughput on non-tensor workloads.
Which variant offers higher dense FP16 performance?▾
The RTX 3090 reaches 71 TFLOPS dense FP16 while the RTX 2080 Ti reaches 40.3 TFLOPS dense FP16. Both figures exclude sparsity.
What TDP values apply to each GPU family?▾
The RTX 2080 Ti family lists 215 W TDP and the RTX 3090 family lists 350 W TDP. These values remain constant across variants within each family.
Do the interconnects differ beyond NVLink?▾
The RTX 2080 Ti uses PCIe 3.0 while the RTX 3090 uses PCIe 4.0. Both retain NVLink support as a shared interconnect option.
How does memory bandwidth affect batch sizing?▾
The RTX 2080 Ti bandwidth of 448 GB/s limits batch size sooner than the 936 GB/s bandwidth of the RTX 3090. Larger batches become feasible on the higher bandwidth variant.
Which is cheaper to rent, the RTX 2080 Ti or the RTX 3090?▾
Cloud rental prices for both the RTX 2080 Ti and RTX 3090 vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the RTX 2080 Ti have compared to the RTX 3090?▾
The RTX 2080 Ti has 11 GB of GDDR6 memory. The RTX 3090 has 24 GB of GDDR6X memory.
Can I find RTX 2080 Ti and RTX 3090 GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the RTX 2080 Ti and the RTX 3090?▾
The RTX 2080 Ti uses the Turing architecture (2018) while the RTX 3090 uses Ampere (2020). The RTX 3090 delivers 1.8x the dense FP16 throughput (71 vs 40.3 TFLOPS, both without sparsity) and 2.1x the memory bandwidth of the RTX 2080 Ti.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the RTX 2080 Ti and the RTX 3090. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent RTX 2080Every current offer by provider, daily price history and a price alert.
- Rent RTX 3090Every current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.