NVIDIA H100 rental: early access
Hopper · SXM (being confirmed)
We’re collecting early-access requests. We’re placing our capacity in Uzbekistan. We don’t publish prices yet. We’ll confirm availability in our reply.
H100
Request H100We’ll reply with terms for your workload. Nothing to pay before the contract.
Estimate usage- Memory per GPU
- 80 GB HBM3
- Memory bandwidth
- 3.35 TB/s
- GPU interconnect
- NVLink 900 GB/s
NVIDIA H100 specifications
- Architecture
- Hopper
- Announced
- 2022
- Memory
- 80 GB
- Memory type
- HBM3
- Memory bandwidth
- 3.35 TB/s
- FP32
- 67 TFLOPS
- FP16/BF16, dense
- 989.4 TFLOPS
- FP8, dense
- 1,978.9 TFLOPS
- FP4, dense
- none
- FP64
- 34 TFLOPS
- FP64 Tensor Core
- 67 TFLOPS
- RT cores
- no
- NVENC/NVDEC
- NVENC 0, NVDEC 7
- MIG
- up to 7 instances
- GPU interconnect
- NVLink 900 GB/s
- Power (TDP/TGP)
- up to 700 W
- Form factor
- SXM (being confirmed)
Memory is specified per GPU. Multiple GPUs have separate memory: using a larger model across them requires compatible software and model partitioning. NVLink does not make them one GPU.
Other variants: H100 NVL (opens in a new tab), H100 PCIe (opens in a new tab)
The H100 form factor is still being confirmed; memory, its bandwidth and other specifications depend on it. Specs from NVIDIA’s official materials, checked 26 September 2026.
The H100 by workload
- Inference: LLMs up to 32B in BF16 on one GPU
- Fine-tuning: QLoRA up to 70B, LoRA up to 14B on one GPU
- Training from scratch: models up to 3B on one GPU
- Rendering: no RT cores
- FP64 computing: 34 TFLOPS, Tensor Core 67 TFLOPS
An estimate from open formulas, not a benchmark or an invoice.
Servers with the NVIDIA H100
Server configuration (CPU, RAM, disk, network) is being confirmed.
Sizing assumption: up to 8 GPUs per server. We’ll confirm the actual configuration in our reply.
More than 8 GPUs? Discuss a clusterSources
Similar GPUs
- NVIDIA A100
80 GB HBM2e · 2.04 TB/s · NVLink
H100 leads on 5 of 6 metrics. H100 has more FP32 (67 vs 19.5 TFLOPS) and FP64 Tensor Core throughput (67 vs 19.5 TFLOPS). Equal: memory size.
- NVIDIA H200
141 GB HBM3e · 4.8 TB/s · NVLink
H200 leads on 2 of 7 metrics. H200 has more memory (141 vs 80 GB) and memory bandwidth (4.8 vs 3.35 TB/s). Equal: FP32, FP16/BF16, FP8, FP64 Tensor Core, NVLink.
Dense FP16/BF16 and FP8 from the H100 SXM5 column of NVIDIA’s whitepaper: for the H200, NVIDIA lists only with-sparsity figures, the same as the H100 SXM’s.
We’ll reply with terms for your workload. Nothing to pay before the contract.