Specifications Compared
| Spec | B300 SXM6 | RTX 5090 |
|---|---|---|
| TDP | 1400W | 575W |
| VRAM | 262 GB | 32 GB |
| CUDA Cores | Not published | 21,760 |
| FP4 (dense) | 13,500 TFLOPS | 1,676 TFLOPS |
| FP8 (dense) | 4,500 TFLOPS | 419 TFLOPS |
| Memory Type | HBM3e | GDDR7 |
| Architecture | Blackwell Ultra | Blackwell |
| FP16 (dense) | 2,250 TFLOPS | 209.5 TFLOPS |
| Form Factors | SXM6 | PCIe |
| INT8 (dense) | 187.5 TOPS | 838 TOPS |
| Interconnect | NVLink, PCIe 6.0, InfiniBand | PCIe 5.0 |
| Tensor Cores | Not published | 680 |
| FP32 Performance | 75 TFLOPS | 104.8 TFLOPS |
| FP64 Performance | 1.25 TFLOPS | 1.6 TFLOPS |
| Memory Bandwidth | 8,000 GB/s | 1,792 GB/s |
| FP4 (with sparsity) | 18,000 TFLOPS | 3,352 TFLOPS |
| FP8 (with sparsity) | 9,000 TFLOPS | 838 TFLOPS |
| FP16 (with sparsity) | 4,500 TFLOPS | 419 TFLOPS |
| INT8 (with sparsity) | 375 TOPS | 1,676 TOPS |
Performance Analysis
The B300 SXM6 delivers 2250 TFLOPS FP16 dense throughput while the RTX 5090 delivers 209.5 TFLOPS FP16 dense throughput, producing a ratio of roughly 10.7 times higher dense FP16 performance on the B300 SXM6. FP32 throughput stands at 75 TFLOPS for the B300 SXM6 family against 104.8 TFLOPS for the RTX 5090 family. Memory bandwidth of 8000 GB/s on the B300 SXM6 family supports substantially larger batch sizes during training or inference than the 1792 GB/s bandwidth on the RTX 5090 family. FP16 dense figures must be compared only to other FP16 dense figures and FP16 with sparsity figures only to other FP16 with sparsity figures such as 4500 TFLOPS versus 419 TFLOPS.
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.
B300 SXM6
1 provider in stock, 2 offers (cheapest per provider shown). All B300 SXM6 offers, price history and alerts
Notify me when B300 SXM6 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.50/GPU-hr.
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 B300 SXM6
The B300 SXM6 variant suits deployments that need 262 GB HBM3e capacity and SXM6 form factor with NVLink interconnect. Large scale model training benefits from the 2250 TFLOPS FP16 dense throughput and 8000 GB/s bandwidth shared across the B300 family when batch sizes exceed what 32 GB allows.
When to Choose the RTX 5090
The RTX 5090 variant fits systems limited to PCIe slots and 575W TDP envelopes. Tasks that fit within 32 GB GDDR7 memory and require only 209.5 TFLOPS FP16 dense throughput gain from the lower power draw and PCIe 5.0 interconnect of this specific model.
Use Cases
The B300 SXM6 variant supplies 262 GB HBM3e memory and 2250 TFLOPS FP16 dense throughput that accommodate models too large for 32 GB.
Batch sizes scale with the 8000 GB/s bandwidth and 4500 TFLOPS FP8 dense throughput of the B300 SXM6 family.
The 262 GB capacity on the B300 SXM6 variant holds full precision weights and optimizer states that exceed the 32 GB limit of the RTX 5090 variant.
The RTX 5090 variant at 575W TDP and 32 GB GDDR7 memory handles typical diffusion workloads without requiring the 1400W TDP of the B300 SXM6 variant.
FP64 capable workloads benefit from the 75 TFLOPS FP32 and high bandwidth of the B300 SXM6 family when precision and memory volume matter.
Frequently Asked Questions
What is the memory difference between B300 SXM6 and RTX 5090?▾
The B300 SXM6 variant contains 262 GB HBM3e while the RTX 5090 variant contains 32 GB GDDR7 for a difference of 230 GB.
How does FP16 performance compare between these GPUs?▾
The B300 SXM6 family provides 2250 TFLOPS FP16 dense throughput and the RTX 5090 family provides 209.5 TFLOPS FP16 dense throughput.
Which GPU uses more power?▾
The B300 SXM6 variant operates at 1400W TDP while the RTX 5090 variant operates at 575W TDP.
What interconnects does each GPU support?▾
The B300 SXM6 variant supports NVLink, PCIe 6.0 and InfiniBand while the RTX 5090 variant supports PCIe 5.0.
Can the RTX 5090 run models that require more than 32 GB?▾
No model that exceeds 32 GB VRAM can run on the RTX 5090 variant whereas the B300 SXM6 variant accommodates up to 262 GB.
What architecture do both GPUs share?▾
Both the B300 SXM6 and RTX 5090 variants belong to the 2025 Blackwell generation with the B300 using Blackwell Ultra.
Which is cheaper to rent, the B300 SXM6 or the RTX 5090?▾
Cloud rental prices for both the B300 SXM6 and RTX 5090 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 B300 SXM6 have compared to the RTX 5090?▾
The B300 SXM6 has 262 GB of HBM3e memory. The RTX 5090 has 32 GB of GDDR7 memory.
Can I find B300 SXM6 and RTX 5090 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 B300 SXM6 and the RTX 5090?▾
The B300 SXM6 uses the Blackwell Ultra architecture (2025) while the RTX 5090 uses Blackwell (2025). The B300 SXM6 delivers 10.7x the dense FP16 throughput (2,250 vs 209.5 TFLOPS, both without sparsity) and 4.5x the memory bandwidth of the RTX 5090.
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 B300 SXM6 and the RTX 5090. 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 B300Every current offer by provider, daily price history and a price alert.
- Rent RTX 5090Every 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.