Specifications Compared
| Spec | B300 | V100 |
|---|---|---|
| TDP | 1400W | 300W |
| VRAM | 262-288 GB | 16-32 GB |
| CUDA Cores | Not published | 5,120 |
| FP4 (dense) | 13,500 TFLOPS | Not published |
| FP8 (dense) | 4,500 TFLOPS | Not published |
| Memory Type | HBM3e | HBM2 |
| Architecture | Blackwell Ultra | Volta |
| FP16 (dense) | 2,250 TFLOPS | 125 TFLOPS |
| Form Factors | SXM6 | SXM2, PCIe |
| INT8 (dense) | 187.5 TOPS | Not published |
| Interconnect | NVLink, PCIe 6.0, InfiniBand | NVLink, PCIe 3.0 |
| Tensor Cores | Not published | 640 |
| FP32 Performance | 75 TFLOPS | 15.7 TFLOPS |
| FP64 Performance | 1.25 TFLOPS | 7.8 TFLOPS |
| Memory Bandwidth | 8,000 GB/s | 900 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 |
Performance Analysis
The FP16 dense rating of 2250 TFLOPS on the B300 exceeds the FP16 dense rating of 125 TFLOPS on the V100 by a factor of 18. This gap means training workloads complete matrix operations faster on the B300 while inference tasks process larger token volumes per step. Memory bandwidth of 8000 GB/s on the B300 versus 900 GB/s on the V100 permits batch sizes up to eight times larger before memory stalls occur during data movement. The B300 FP16 with sparsity rating of 4500 TFLOPS has no direct counterpart on the V100 so only dense figures allow valid comparison between the two GPUs.
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
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| RunPod | global | 1 | $0.50 | — | Deploy |
| VERDA | FIN-HEL | 1 | $10.18 | — | Deploy |
| Lyceum | Europe | 1 | $11.09 | — | Deploy |
3 providers in stock, 4 offers (cheapest per provider shown). All B300 offers, price history and alerts
V100
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| VERDA | FIN-HEL | 2 | $0.22 | $0.45 | Deploy |
| Ori | lille-3 | 1 | $0.83 | — | Deploy |
| Paperspace | ca1 | 1 | $2.30 | — | Deploy |
3 providers in stock, 73 offers (cheapest per provider shown). All V100 offers, price history and alerts
Notify me when B300 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
The B300 suits workloads that require 262 to 288 GB HBM3e VRAM and 8000 GB/s memory bandwidth for models exceeding 32 GB in size. Its FP16 dense performance of 2250 TFLOPS supports accelerated training cycles on large language models where the V100 FP16 dense performance of 125 TFLOPS would extend run times substantially.
When to Choose the V100
The V100 fits deployments limited to 300W TDP and existing SXM2 or PCIe slots that cannot accommodate the B300 1400W requirement. Its 15.7 TFLOPS FP32 rating remains adequate for legacy scientific codes that do not benefit from the B300 75 TFLOPS FP32 rating.
Use Cases
The B300 FP16 dense rating of 2250 TFLOPS exceeds the V100 FP16 dense rating of 125 TFLOPS by a factor of 18.
The B300 memory bandwidth of 8000 GB/s supports larger batch sizes than the V100 memory bandwidth of 900 GB/s.
The B300 262 to 288 GB HBM3e VRAM accommodates models larger than the V100 16 to 32 GB HBM2 VRAM limit.
The B300 FP16 dense rating of 2250 TFLOPS processes diffusion steps faster than the V100 FP16 dense rating of 125 TFLOPS.
The V100 300W TDP operates in power constrained environments where the B300 1400W TDP exceeds available limits.
Frequently Asked Questions
What FP16 performance does the B300 deliver?▾
The B300 delivers 2250 TFLOPS in dense mode and 4500 TFLOPS with sparsity. These figures exceed the V100 FP16 dense rating of 125 TFLOPS.
What is the TDP of the B300?▾
The B300 TDP is 1400W. This value is higher than the V100 TDP of 300W.
Does the V100 support FP8?▾
The V100 does not publish an FP8 rating. The B300 provides FP8 dense performance of 4500 TFLOPS.
What interconnect does the B300 use?▾
The B300 uses NVLink together with PCIe 6.0 and InfiniBand. The V100 uses NVLink with PCIe 3.0.
What FP32 performance does each GPU offer?▾
The B300 offers 75 TFLOPS FP32 while the V100 offers 15.7 TFLOPS FP32.
Which is cheaper to rent, the B300 or the V100?▾
Cloud rental prices for both the B300 and V100 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 have compared to the V100?▾
The B300 has 262 to 288 GB of HBM3e memory. The V100 has 16 to 32 GB of HBM2 memory.
Can I find B300 and V100 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 and the V100?▾
The B300 uses the Blackwell Ultra architecture (2025) while the V100 uses Volta (2017). The B300 delivers 18.0x the dense FP16 throughput (2,250 vs 125 TFLOPS, both without sparsity) and 8.9x the memory bandwidth of the V100.
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 and the V100. 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 V100Every 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.