Specifications Compared
| Spec | B300 SXM6 | RTX 3090 |
|---|---|---|
| TDP | 1400W | 350W |
| VRAM | 262 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 | Not published |
| Form Factors | SXM6 | PCIe |
| INT8 (dense) | 187.5 TOPS | Not published |
| Interconnect | NVLink, PCIe 6.0, InfiniBand | NVLink |
| 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 | Not published |
| INT8 (with sparsity) | 375 TOPS | Not published |
| FP16 (vendor figure, sparsity not specified) | Not published | 35.6 TFLOPS |
Performance Analysis
The B300 SXM6 delivers FP16 dense performance of 2250 TFLOPS compared to the RTX 3090 FP16 figure of 35.6 TFLOPS which allows substantially larger model training and inference workloads on the newer GPU. Memory bandwidth reaches 8000 GB/s on the B300 SXM6 against 936 GB/s on the RTX 3090 so batch sizes during LLM operations can increase markedly without hitting memory limits. FP32 throughput stands at 75 TFLOPS dense for the B300 SXM6 versus 35.6 TFLOPS for the RTX 3090 while the 262 GB capacity versus 24 GB capacity further separates the two for memory intensive tasks.
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
RTX 3090
| 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, 10 offers (cheapest per provider shown). All RTX 3090 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 large scale LLM training because its 262 GB HBM3e capacity and 8000 GB/s bandwidth support models that exceed the limits of smaller memory configurations. Its FP16 dense rating of 2250 TFLOPS enables faster iteration on scientific computing workloads that require high tensor throughput.
When to Choose the RTX 3090
The RTX 3090 variant fits smaller fine tuning jobs and Stable Diffusion tasks where 24 GB GDDR6X memory proves adequate and the 350W TDP keeps power draw low. Its PCIe form factor simplifies integration into standard servers without the need for SXM6 infrastructure.
Use Cases
The B300 SXM6 variant provides 262 GB HBM3e memory and FP16 dense throughput of 2250 TFLOPS that accommodate large models the RTX 3090 cannot fit.
FP8 dense performance of 4500 TFLOPS on the B300 SXM6 variant combined with 8000 GB/s bandwidth supports higher throughput inference than the RTX 3090 can achieve.
Both GPUs handle fine tuning yet the RTX 3090 variant with 24 GB memory works for smaller models while the B300 SXM6 variant scales to larger ones.
The RTX 3090 variant delivers sufficient 35.6 TFLOPS FP16 performance and 24 GB GDDR6X memory for image generation tasks at lower 350W power consumption.
FP32 throughput of 75 TFLOPS on the B300 SXM6 variant and its 262 GB capacity enable complex simulations beyond the RTX 3090 capabilities.
Frequently Asked Questions
How does memory bandwidth differ between these GPUs?▾
Memory bandwidth reaches 8000 GB/s on the B300 SXM6 variant compared to 936 GB/s on the RTX 3090 variant allowing larger batch processing on the former.
What are the FP16 performance figures for each GPU?▾
The B300 SXM6 variant lists FP16 dense performance at 2250 TFLOPS while the RTX 3090 variant lists an FP16 figure of 35.6 TFLOPS without sparsity specification.
Which form factor applies to the B300 SXM6 variant?▾
The B300 SXM6 variant uses the SXM6 form factor and supports NVLink along with PCIe 6.0 and InfiniBand interconnects unlike the PCIe form factor of the RTX 3090 variant.
What TDP values are associated with these two variants?▾
The B300 SXM6 variant carries a TDP of 1400W while the RTX 3090 variant carries a TDP of 350W reflecting their different power envelopes.
Which architecture powers the B300 SXM6 variant?▾
The B300 SXM6 variant operates on Blackwell Ultra architecture released in 2025 whereas the RTX 3090 variant operates on Ampere architecture released in 2020.
Which is cheaper to rent, the B300 SXM6 or the RTX 3090?▾
Cloud rental prices for both the B300 SXM6 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 B300 SXM6 have compared to the RTX 3090?▾
The B300 SXM6 has 262 GB of HBM3e memory. The RTX 3090 has 24 GB of GDDR6X memory.
Can I find B300 SXM6 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 B300 SXM6 and the RTX 3090?▾
The B300 SXM6 uses the Blackwell Ultra architecture (2025) while the RTX 3090 uses Ampere (2020). The B300 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.
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 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 B300Every 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.