Rent GB300 NVL72
Compare live on-demand and spot rental prices across 97+ cloud providers. Blackwell Ultra rack-scale system. 72 GPUs + 36 Grace Ultra CPUs. Highest throughput available in 2026.
Choosing the right billing model for GB300 NVL72
Provision and terminate at any time. Ideal for development, short experiments, and workloads with unpredictable duration.
Instances can be reclaimed when demand spikes. Best for fault-tolerant batch jobs, training with checkpointing, and preprocessing.
Lock in a rate for 1–3 months. Right for sustained production inference or long training runs where cost predictability matters.
Best use cases
- Next-gen frontier training
- Trillion-param inference
- Rack-scale AI
GB300 NVL72 — Specs & Benchmarks
Performance bars, compute tiers (FP32/FP16/BF16/FP8/INT8), memory specs, LLM model size guidance, and related GPU comparisons.
GB300 NVL72 Rental Guide
Renting the GB300 NVL72 makes sense when your workload requires 288GB of HBM3e memory and 7500 TFLOPS of FP16 compute. The most common use cases are Next-gen frontier training, Trillion-param inference, Rack-scale AI. Before committing to a rental, verify that your model and batch size fit within 288GB — a 70B parameter model requires approximately 140GB at FP16, which would require two GB300 NVL72 instances with tensor parallelism.
For fault-tolerant batch workloads — preprocessing, offline inference, or training with checkpointing — spot instances typically save 40–70% vs on-demand rates. The GB300 NVL72's 288GB VRAM makes it well-suited for long-running batch jobs where interruption recovery is manageable. On-demand instances give you full control with no commitment — ideal for development, short experiments, and workloads with unpredictable duration. Most providers bill per second or per minute, so short jobs are not penalized by hourly minimums.
For sustained production inference serving, reserved instances (1–3 month commitments) typically offer 20–35% savings vs on-demand. The GB300 NVL72's high throughput makes it cost-effective for high-volume inference where per-token cost matters. When comparing providers, look beyond the headline hourly rate: check region availability (latency matters for interactive inference), spot interruption frequency, and whether the provider offers per-second billing. Use the GPU cost calculator to model total cost across different billing models and utilization rates before choosing a provider.
Frequently Asked Questions
How much does it cost to rent a GB300 NVL72?
GB300 NVL72 on-demand rental prices vary by provider and region. On-demand rates typically range based on availability and provider margins — use the comparison table above to see current live rates across all providers. Spot instances are generally 40–70% cheaper than on-demand but can be interrupted. Monthly cost estimates (hourly rate × 730 hours) are shown in the table for sustained workloads.
Which cloud provider has the cheapest GB300 NVL72?
The cheapest GB300 NVL72 provider changes as providers update their pricing. The comparison table above shows live rates sorted by price, so the cheapest option is always at the top. Factors beyond headline price include region (latency to your users), availability (high/medium/low), and billing granularity (per-second vs per-hour minimums).
What can I run on a GB300 NVL72?
With 288GB of HBM3e, the GB300 NVL72 can run LLM models up to approximately 144B parameters at FP16, 288B at INT8, or 576B at INT4/GGUF quantization. Common workloads include: Next-gen frontier training, Trillion-param inference, Rack-scale AI. Blackwell Ultra rack-scale system. 72 GPUs + 36 Grace Ultra CPUs. Highest throughput available in 2026.
Should I use on-demand or spot pricing for GB300 NVL72?
Spot instances save 40–70% vs on-demand but can be interrupted when the provider needs capacity back. Use spot for: batch inference jobs, training runs with checkpointing, preprocessing pipelines, and any workload that can tolerate interruption and restart. Use on-demand for: production inference serving, interactive workloads, and jobs that cannot be interrupted. Most providers bill per second, so short on-demand jobs are not penalized by hourly minimums.
How does the GB300 NVL72 compare to the H100 for cloud rental?
The H100 80GB delivers 1,979 TFLOPS FP16 with 3,350 GB/s HBM3 bandwidth, compared to the GB300 NVL72's 7500 TFLOPS FP16 and 16000 GB/s bandwidth. The H100 is significantly more expensive — typically $2.50–$5.00/hr vs lower rates for the GB300 NVL72. For workloads that fit within 288GB and don't require FP8 precision, the GB300 NVL72 often delivers better cost-per-token than the H100.
What is the memory bandwidth of the GB300 NVL72 and why does it matter?
The GB300 NVL72 has 16000 GB/s of memory bandwidth. For LLM inference, memory bandwidth is often more important than raw TFLOPS — each autoregressive token generation reads the full model weight matrix from VRAM, so bandwidth directly determines tokens-per-second throughput. Higher bandwidth means faster inference for the same model at the same batch size. For batch inference (processing many requests simultaneously), compute throughput becomes more important.
Can I use the GB300 NVL72 for Stable Diffusion or image generation?
Yes — the GB300 NVL72 is well-suited for Stable Diffusion and image generation workloads. Image generation is primarily FP32 and FP16 compute-bound, and the GB300 NVL72's 120 TFLOPS FP32 throughput determines images-per-second. The 288GB VRAM fits SDXL (requires ~6GB) and most ControlNet pipelines. For high-throughput image generation at scale, compare cost-per-image across providers using the GPU cost calculator.