NVIDIA Blackwell
Rent B200 servers, reserved from data centers
B200 is the first Blackwell data-center GPU, rented mostly as HGX B200 eight-GPU servers. It added FP4 and roughly doubled the memory of an H100, which is why it replaced H100 for new training clusters.
- Memory per GPU
- 180 GB HBM3e
- Architecture
- Blackwell
- Listings
- On request
- From
- Ask
B200 capacity listed now
No B200 capacity is listed right now. Send a request and we will source it from our owners.
Tell us what you needWhat B200 is good for
- Training on eight-GPU nodes and multi-node clusters
- FP8 and FP4 inference of large models
What to ask before you reserve B200 capacity
- The exact server configuration and local storage.
- How the servers are interconnected (InfiniBand or RoCE, and at what speed per GPU) if you will train across nodes.
- Whether the price covers storage, egress and support, or only the GPU-hours.
- The uptime they commit to, and what you get back when they miss it.
Questions
- How much does it cost to rent a B200?
- Owners set their own price per GPU-hour, which depends on the number of servers, the term and the start date. Send a request with what you need and we come back with offers.
- What is the minimum term for reserved B200 capacity?
- Usually one month or more, set by each owner. Longer terms usually get a lower price per GPU-hour.
- How much memory does a B200 have?
- 180 GB HBM3e per GPU (NVIDIA Blackwell).
- Can I rent a single B200 server?
- Yes, where the owner allows it: each listing shows how many servers it has and you can ask for one or for all of them.
Tell us what you need
Sign in to send a request. It opens a conversation with the owners and the Paralon team, and you get an email for every reply.
Sign in to requestFree, with Google, GitHub or an email code. No commitment.