NVIDIA Rubin R100 — which NVIDIA itself calls simply the Rubin GPU — is the generational successor to Blackwell Ultra (B300). NVIDIA has announced 288 GB of HBM4, up to 22 TB/s of memory bandwidth, 50 PFLOPS of dense FP4 compute and NVLink 6 at 3.6 TB/s. NVIDIA has indicated sampling around Q4 2026 with broader cloud availability expected in 2027; no pricing has been published. Register interest to be notified as capacity planning progresses.
| GPU memory | 288 GB HBM4 |
|---|---|
| Memory bandwidth | Up to 22 TB/s |
| Dense compute (FP4) | 50 PFLOPS |
| Interconnect | NVLink 6 · 3.6 TB/s |
| Availability | Sampling ~Q4 2026 · pre-order registration only |
R100 has not shipped. Join the pipeline and Arvica will contact you with pricing and availability once capacity opens.
Rubin
Exact GPU variant, CPU, RAM and interconnect depend on the confirmed instance. Memory values are hardware references, not allocated resources.
Manufacturer specifications ↗Not offered on demand. Pricing and delivery are set in an Arvica proposal.
Request capacity proposal →Request reserved capacity through an Arvica proposal. Location, start time and access environment are confirmed before provisioning.
Not offered on demand. Pricing and delivery are set in an Arvica proposal.
Term, volume and dedicated-capacity prices are set in an accepted Arvica proposal. Configuration, region and delivery are confirmed in your proposal.
Availability confirmed before order acceptance. Taxes and additional services are confirmed before payment.
Consider R100 for trillion-parameter inference at FP4 precision and multi-node training runs where Blackwell-generation memory bandwidth becomes the limiting factor. This is pre-order planning only — no confirmed delivery date, price or configuration exists yet.
Compare B300 and GB300 NVL72 for current-generation deployments; capacity is confirmed for the requested configuration and start date. R100 enquiries do not guarantee a delivery date, price or configuration until the product and supply are confirmed.
288 GB HBM4 with up to 22 TB/s of bandwidth is the manufacturer-announced reference. Rubin platform memory, interconnect and system configurations have not been finalised publicly; confirm details as they are released.
NVIDIA has announced NVLink 6 at 3.6 TB/s for Rubin-generation GPUs. Do not assume node count, NVLink domain or host CPU for a rack-scale system until a partner platform is announced.
Expect a new CUDA and driver baseline for Rubin. Plan a validation window for frameworks, kernels and container images once early access becomes available.
NVIDIA hardware reference ↗ · Selection guidance is Arvica's assessment; validate it against your workload
Specify the OS, framework and container image version. Arvica confirms the driver and GPU compatibility before activation. A template name is not a software licence or a guaranteed preinstalled image.
Save an SSH public key during configuration. Keep the private key on your own device. The verified deployment record provides the actual host and login user once access is ready.
Separate boot disk, datasets, model weights and checkpoints in your capacity plan. Confirm persistence, backup ownership, attachment rules and deletion behaviour before relying on a volume.
Confirm ingress, egress, public IP access and private networking where required. For regulated or location-sensitive data, specify the required region in advanced settings before submitting.
Once Arvica supplies verified access, connect using your private key and the exact host/user shown in your instance. Then inspect the allocated GPUs and topology.
ssh -i ~/.ssh/your_key USER@HOST nvidia-smi nvidia-smi topo -m
Replace USER and HOST with your own deployment details. These commands inspect an existing machine; they do not provision one.
Parameter count × bytes per weight estimates weights only. Add KV cache, activations, temporary tensors and framework overhead. Training additionally needs gradients and optimiser state.
Record model version, precision, input/output length, concurrency, latency and error rate together. Compare the cost of a completed job or successful request under the same conditions.
Include all allocated GPUs, runtime, storage, networking, taxes and support. Monthly projections use 730 hours for comparison; your contract defines the billable period and minimum term.
Define your GPU allocation, interconnect, storage, location and commitment. Arvica prepares a capacity proposal around the workload.
Request capacity ↗Model fit and throughput depend on precision, software, batch size, context and system topology. Compare workload estimates rather than an unsupported tokens-per-second promise.
Training cost calculator →Consider R100 for trillion-parameter inference at FP4 precision and multi-node training runs where Blackwell-generation memory bandwidth becomes the limiting factor. This is pre-order planning only — no confirmed delivery date, price or configuration exists yet.
288 GB HBM4 with up to 22 TB/s of bandwidth is the manufacturer-announced reference. Rubin platform memory, interconnect and system configurations have not been finalised publicly; confirm details as they are released.
Expect a new CUDA and driver baseline for Rubin. Plan a validation window for frameworks, kernels and container images once early access becomes available.
NVIDIA has announced NVLink 6 at 3.6 TB/s for Rubin-generation GPUs. Do not assume node count, NVLink domain or host CPU for a rack-scale system until a partner platform is announced.
Do not assume so. Resource allocation, storage and reserved commitments may continue billing. Check the contract and request the appropriate lifecycle action through support.
Retention depends on the agreed storage configuration. Export data and confirm backup and volume retention before requesting termination.
Current configurations enter Arvica capacity review. Running status is shown only after infrastructure is verified.
It is not offered on demand. Price, currency, delivery and terms are set in your Arvica proposal; storage, network, tax and service charges are itemised before you commit.
Use the enterprise capacity path for multi-node networking and reserved allocations.
| GPU | Memory reference | Best-fit decision |
|---|---|---|
| R100 | 288 GB HBM4 | Consider R100 for trillion-parameter inference at FP4 precision and multi-node training runs where Blackwell-generation memory bandwidth becomes the limiting factor. This is pre-order planning only — no confirmed delivery date, price or configuration exists yet. |
| H200 | 141 GB HBM3e | Test H200 when model weights, KV cache and concurrent requests compete for memory. Extra capacity can reduce the need to split a workload across GPUs, depending on precision and runtime overhead. |
| B300 | 288 GB HBM3e | Evaluate B300 when model state, activations or KV cache constrain your current deployment. Use a representative model and concurrency target to decide whether fewer larger GPUs improve total cost. |
| GB300 NVL72 | 72-GPU system | Evaluate rack-scale capacity for sustained large-model inference or distributed training with demanding communication requirements. Supply the parallelism plan and service-level objectives with your request. |
| Configuration | Practical difference | Confirm before ordering |
|---|---|---|
| SXM · VM · 288 GB HBM4 | Guest OS and assigned resources within a virtual machine | GPU count, NVLink/NVSwitch topology, inter-node fabric and NUMA placement |
| SXM · Bare Metal · 288 GB HBM4 | Dedicated physical host configuration; host access follows the confirmed service | GPU count, NVLink/NVSwitch topology, inter-node fabric and NUMA placement |
Weights alone are approximately parameters × bytes per parameter. A 7B model at BF16 needs about 14 GB just for weights; a 70B model about 140 GB. Add KV cache, activations, framework buffers and training state. These are arithmetic estimates, not fit guarantees.
Compare the same model revision, precision, sequence length and concurrency. Record time to first token, p95 latency, output tokens/s, peak memory and full instance cost. Training comparisons should include step time and convergence at the same quality target.
Manufacturer specifications are linked below. No Arvica application-throughput benchmark is published for this configuration yet. Request a workload-specific acceptance test before making performance commitments.
NVIDIA ↗Configure dedicated PCIe / SXM, virtual-machine and bare-metal capacity with Arvica. Submit your requirements for a deployment proposal.
2 configurations available for enquiry
