Specifications Compared
| Spec | GB300 SXM6 | RTX 3090 Ti |
|---|---|---|
| TDP | 1400W | 350W |
| VRAM | 288 GB | 24 GB |
| CUDA Cores | Not published | 10,496 |
| FP4 (dense) | 13,500 TFLOPS | Not published |
| FP8 (dense) | 4,500 TFLOPS | Not published |
| Memory Type | HBM3e | GDDR6X |
| Architecture | Blackwell Ultra | Ampere |
| FP16 (dense) | 2,250 TFLOPS | 71 TFLOPS |
| Form Factors | SXM6 | PCIe |
| INT8 (dense) | 187.5 TOPS | 284 TOPS |
| Interconnect | NVLink, PCIe 6.0, InfiniBand | NVLink, PCIe 4.0 |
| Tensor Cores | Not published | 328 |
| FP32 Performance | 75 TFLOPS | 35.6 TFLOPS |
| FP64 Performance | 1.25 TFLOPS | Not published |
| Memory Bandwidth | 8,000 GB/s | 936 GB/s |
| FP4 (with sparsity) | 18,000 TFLOPS | Not published |
| FP8 (with sparsity) | 9,000 TFLOPS | Not published |
| FP16 (with sparsity) | 4,500 TFLOPS | 142 TFLOPS |
| INT8 (with sparsity) | 375 TOPS | 568 TOPS |
Performance Analysis
The GB300 SXM6 delivers 2250 TFLOPS dense FP16 and 75 TFLOPS FP32 while the RTX 3090 Ti delivers 71 TFLOPS dense FP16 and 35.6 TFLOPS FP32. This dense FP16 advantage of roughly thirty two times allows the GB300 SXM6 to complete matrix operations in training workloads at substantially higher throughput than the RTX 3090 Ti. Memory bandwidth stands at 8000 GB/s for the GB300 SXM6 family and 936 GB/s for the RTX 3090 Ti family so the former supports larger batch sizes before memory capacity of 288 GB becomes the limit. Sparse FP16 figures reach 4500 TFLOPS on the GB300 SXM6 and 142 TFLOPS on the RTX 3090 Ti yet the same ratio pattern holds when comparing like with like.
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.
GB300 SXM6
GB300 SXM6 is not offered on-demand by any provider we track right now. See the GB300 SXM6 rental page for last-seen listed prices and a price alert.
RTX 3090 Ti
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| Vast.ai | Finland, FI | 4 | $0.27 | $1.07 | Deploy |
| LeaderGPU | The Netherlands | 8 | $0.29 | $2.29 | Deploy |
2 providers in stock, 9 offers (cheapest per provider shown). All RTX 3090 Ti offers, price history and alerts
Notify me when GB300 SXM6 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold.
QuantaCloud
Comparing B-series options? Get one quote for all of them.
Skip the per-provider sales calls. Reserved and cluster B-series configurations from 16 to 1024+ GPUs with InfiniBand fabric, 3 to 12 month terms. One quote at partner rates, 24h turnaround.
When to Choose the GB300 SXM6
The GB300 SXM6 variant suits workloads that require the full 288 GB HBM3e capacity together with 8000 GB/s bandwidth and 2250 TFLOPS dense FP16. Large scale training jobs that exceed the 24 GB limit of the RTX 3090 Ti variant benefit directly from these shared family figures.
When to Choose the RTX 3090 Ti
The RTX 3090 Ti variant fits tasks constrained by the 350W TDP and the 24 GB GDDR6X capacity where the 71 TFLOPS dense FP16 and 35.6 TFLOPS FP32 remain sufficient. Smaller inference or fine tuning runs that fit within PCIe form factor limits avoid the 1400W TDP of the GB300 SXM6 variant.
Use Cases
The GB300 SXM6 variant supplies 288 GB HBM3e and 2250 TFLOPS dense FP16 that exceed the 24 GB and 71 TFLOPS dense FP16 of the RTX 3090 Ti variant.
The GB300 SXM6 variant supports larger batch sizes with 8000 GB/s bandwidth and 4500 TFLOPS dense FP8 compared with the RTX 3090 Ti variant figures.
The GB300 SXM6 variant accommodates models that require more than 24 GB while delivering 2250 TFLOPS dense FP16 versus 71 TFLOPS dense FP16 on the RTX 3090 Ti variant.
The RTX 3090 Ti variant operates at 350W TDP and provides 71 TFLOPS dense FP16 sufficient for workloads that fit in 24 GB GDDR6X.
The GB300 SXM6 variant offers 75 TFLOPS FP32 while the RTX 3090 Ti variant offers 35.6 TFLOPS FP32 so selection depends on model size relative to 288 GB versus 24 GB.
Frequently Asked Questions
What is the memory difference between the GB300 SXM6 and the RTX 3090 Ti?▾
The GB300 SXM6 variant contains 288 GB HBM3e while the RTX 3090 Ti variant contains 24 GB GDDR6X resulting in a twelve fold capacity gap.
How do the FP16 figures compare between these two GPUs?▾
The GB300 SXM6 variant reaches 2250 TFLOPS dense FP16 and the RTX 3090 Ti variant reaches 71 TFLOPS dense FP16 so the ratio favors the former by more than thirty times.
What TDP values apply to the GB300 SXM6 and the RTX 3090 Ti?▾
The GB300 SXM6 variant carries a 1400W TDP and the RTX 3090 Ti variant carries a 350W TDP as shared family figures for each architecture.
How does memory bandwidth differ between the two models?▾
The GB300 SXM6 family bandwidth measures 8000 GB/s and the RTX 3090 Ti family bandwidth measures 936 GB/s.
Which is cheaper to rent, the GB300 SXM6 or the RTX 3090 Ti?▾
Cloud rental prices for both the GB300 SXM6 and RTX 3090 Ti 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 GB300 SXM6 have compared to the RTX 3090 Ti?▾
The GB300 SXM6 has 288 GB of HBM3e memory. The RTX 3090 Ti has 24 GB of GDDR6X memory.
Can I find GB300 SXM6 and RTX 3090 Ti 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 GB300 SXM6 and the RTX 3090 Ti?▾
The GB300 SXM6 uses the Blackwell Ultra architecture (2025) while the RTX 3090 Ti uses Ampere (2020). The GB300 SXM6 delivers 31.7x the dense FP16 throughput (2,250 vs 71 TFLOPS, both without sparsity) and 8.5x the memory bandwidth of the RTX 3090 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 GB300 SXM6 and the RTX 3090 Ti. 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 GB300Every 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.