GPU Cloud
B200, dedicated.
A single NVIDIA B200 GPU, 180 GB HBM3e on the Blackwell architecture, on an x86 host. $5.49 per hour, billed per minute, the same terms as every other GPUwerk tier.
Rented first come, first served: deploy a B200 when capacity is free, or join its waitlist in the console.
Specifications
Per GPU. The GPU and its memory are yours alone for the rental.
| GPU | B200, Blackwell architecture |
|---|---|
| Memory | 180 GB HBM3e |
| Memory bandwidth | 8 TB/s |
| Precision | FP4 and FP8 with the second-generation Transformer Engine |
| Host | x86 host |
| Tenancy | The GPU is yours alone while you rent it, never shared |
GPU figures from NVIDIA DGX B200. GPUwerk publishes tok/s and training throughput figures only for runs on its own hardware. See the DGX Spark fleet benchmarks for how they are reported.
What would you run on it?
Blackwell with 180 GB per GPU and FP4 support: the step up from Hopper for training and large-model inference.
FP4 and FP8 inference
Native FP4 holds a model of up to about 360B parameters by weights alone; FP8 up to about 180B.
Training and fine-tuning
Runs that need more memory and bandwidth per GPU than Hopper offers.
One GPU instead of two
Models that would otherwise be split across two H100s or H200s.
Poor fit: small models
A model that fits in 24 or 48 GB runs on an L4 or L40S at a fraction of the hourly rate.
Need all eight GPUs of one server? See the 8× B200 server.
What fits in 180 GB
Weights only: memory divided by bytes per parameter. Leave headroom for the KV cache, activations and the runtime, often 10 to 30% more.
| Precision | Per parameter | Largest model, weights only |
|---|---|---|
| FP16 / BF16 | 2 bytes | about 90B parameters |
| FP8 | 1 byte | about 180B parameters |
| FP4 (native on Blackwell) | 0.5 bytes | about 360B parameters |
Billing
| Rate | $5.49 per hour, billed per minute |
|---|---|
| Billing | Per minute, against a prepaid credit balance |
| Fees | No egress fees |
| Commitment | None |
Prices are in USD, excluding applicable tax. Full billing mechanics, including what a stop versus a terminate does, are on the pricing page.
FAQ
Can I rent a B200 now?
Deploy it from the console when capacity is free; while none is, the console offers a waitlist and people in line are emailed one at a time, oldest first. Capacity is not held for anyone: whoever deploys first gets it.
How does billing work on this tier?
The same as every GPUwerk tier: per minute, against a prepaid credit balance, in USD, excluding applicable tax, with no egress fees and no commitment.
Need GPU time today?
A DGX Spark has 128 GB of unified memory and is rentable now, at $0.79/hour billed per minute. First top-up: pay $20, get $30 in credit. Or deploy a B200.