*[DediGPU](https://dedigpu.com/) — Markdown mirror of [https://dedigpu.com/gpu/h100-pcie](https://dedigpu.com/gpu/h100-pcie) · updated 2026-09-02 · index for LLMs: [llms.txt](https://dedigpu.com/llms.txt) · everything: [llms-full.txt](https://dedigpu.com/llms-full.txt)*

NVIDIA · Hopper

# Dedicated NVIDIA H100 PCIe 80 GB server, $810 a month.

The whole card — 80 GB of HBM2e at 2 TB/s — with 16 dedicated vCPU, 128 GB of RAM and 1 TB of NVMe, on a 25 Gbit/s port with free egress. Root in under 5 minutes. Priced from a cost sheet you can read below, with zero margin on the server.

- 1× to 8× cards, PCIe 5.0 · NVLink bridge (pairs)
- 4 regions, same price
- No setup fee, no KYC, crypto balance
- 99.9% SLA credited ×10

- **80 GB** HBM2e per card
- **2 TB/s** memory bandwidth
- **NVLink bridge (pairs)** PCIe 5.0
- **25 Gbit/s** port, $0 egress
- **350 W** board power, in the cost sheet

The cost sheet

## What an H100 PCIe costs us, per card, per month.

Six lines, added up, rounded up to the next dollar. That is the price. The assumptions are the same for every card and are explained on the [pricing page](https://dedigpu.com/pricing#method).

- Hardware $23,000 card + $2,500 chassis share, over 36 months $708.33
- Power 276 kWh at $0.052 · 470 W, 70% load, PUE 1.15 $14.36
- Rack & cooling PCIe chassis, air $25.00
- Network & IP transit share, one IPv4, port $9.00
- Spares & failures 2% of the card price per year $38.33
- Operations monitoring, on-call, provisioning $14.00
- Total rounded up to the next dollar $809.03 → $810

Cheapest published price we found for the same card: $1,278 per month at Hyperstack (reserved) (reserved), checked 2 September 2026 — 37% more than our cost. Where the money comes from, then: options with a normal margin, power bought at scale, full racks, no card network. [Read how](https://dedigpu.com/pricing#margin).

Configurations

## One card to eight. The price is linear.

CPU, RAM and NVMe scale with the cards. Cards share the chassis over PCIe 5.0 · NVLink bridge (pairs).

| Server | GPU memory | CPU | RAM | NVMe | Network | Per month | 12-month rate |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| **1× H100 PCIe** | 80 GB | 16 vCPU | 128 GB | 1 TB | 25 Gbit/s | $810 | $729.00 | [Order](https://dedigpu.com/signup?gpu=h100-pcie&n=1) |
| **2× H100 PCIe** | 160 GB | 32 vCPU | 256 GB | 2 TB | 25 Gbit/s | $1,620 | $1,458.00 | [Order](https://dedigpu.com/signup?gpu=h100-pcie&n=2) |
| **4× H100 PCIe** | 320 GB | 64 vCPU | 512 GB | 4 TB | 25 Gbit/s | $3,240 | $2,916.00 | [Order](https://dedigpu.com/signup?gpu=h100-pcie&n=4) |
| **8× H100 PCIe** | 640 GB | 128 vCPU | 1024 GB | 8 TB | 25 Gbit/s | $6,480 | $5,832.00 | [Order](https://dedigpu.com/signup?gpu=h100-pcie&n=8) |

Per month for a one-month term; the 12-month rate is the same server on a 12-month term (−10 %). Options — extra NVMe, IPv4, 25 Gbit/s uplink, private VLAN — are added on the order form at the prices on the [pricing page](https://dedigpu.com/pricing#options).

Terms

## Prepay longer, pay less per month.

A longer term costs us less to run — one provisioning, no re-image between tenants, a firmer power forecast — and the difference is passed on. The rate is locked for as long as the server renews.

| Term | Discount | Per month | Charged at order | Saved over the term |
| --- | --- | --- | --- | --- |
| **1 month** | cost sheet | $810.00 | $810.00 | — |
| **3 months** | −3 % | $785.70 | $2,357.10 | $72.90 |
| **6 months** | −6 % | $761.40 | $4,568.40 | $291.60 |
| **12 months** | −10 % | $729.00 | $8,748.00 | $972.00 |

For one H100 PCIe; multiply by the card count. Renewal takes the same term at the same rate. [How renewals, grace and suspension work](https://dedigpu.com/docs/terms-and-renewals).

Specifications

## Per card, before you multiply.

- **GPU:** NVIDIA H100 PCIe 80 GB
- **Architecture:** Hopper
- **GPU memory:** 80 GB HBM2e
- **Memory bandwidth:** 2 TB/s
- **Interconnect:** PCIe 5.0 · NVLink bridge (pairs)
- **Form factor:** PCIe, dual-slot, passively cooled
- **Board power:** 350 W
- **CPU per card:** 16 dedicated vCPU
- **System RAM per card:** 128 GB ECC
- **Local NVMe per card:** 1 TB
- **Network:** 25 Gbit/s · one IPv4 · $0 egress
- **Cards per server:** 1×, 2×, 4×, 8×
- **Out-of-band:** IPMI console, power control, virtual media

What fits

## Popular models on 1× H100 PCIe.

Memory needed = parameters × bytes per parameter × 1.2 (KV cache and runtime). Change the card count above and the table follows. [The full guide](https://dedigpu.com/guides/how-much-vram-to-run-an-llm).

| Model | BF16 | FP8 | INT8 | INT4 |
| --- | --- | --- | --- | --- |
| Llama 3.1 8B | 20 GB | 10 GB | 10 GB | 5 GB |
| Mistral Small 3.1 24B | 58 GB | 29 GB | 29 GB | 15 GB |
| Gemma 3 27B | 65 GB | 33 GB | 33 GB | 17 GB |
| Qwen3 32B | 77 GB | 39 GB | 39 GB | 20 GB |
| Llama 3.3 70B | 168 GB | 84 GB | 84 GB | 42 GB |
| Qwen2.5 72B | 173 GB | 87 GB | 87 GB | 44 GB |
| Llama 4 Scout · 109B MoE | 262 GB | 131 GB | 131 GB | 66 GB |
| Mixtral 8x22B · 141B MoE | 339 GB | 170 GB | 170 GB | 85 GB |
| Qwen3 235B-A22B · MoE | 564 GB | 282 GB | 282 GB | 141 GB |
| Llama 3.1 405B | 972 GB | 486 GB | 486 GB | 243 GB |
| DeepSeek-V3 / R1 · 671B MoE | 1611 GB | 806 GB | 806 GB | 403 GB |

Green fits in 80 GB with a working KV cache; red does not. FP8 needs Ada, Hopper, Blackwell or MI300X silicon. MoE models count every expert.

Software

## Pre-installed before you log in.

Pick the system and the template on the order form; serving templates pull the model you name before first boot. [Every template, with its ports](https://dedigpu.com/templates).

### Operating systems

- **Ubuntu 24.04 LTS** Kernel 6.8 · the default for every template
- **Ubuntu 22.04 LTS** Kernel 5.15 HWE · for stacks pinned to CUDA 11.8 / 12.1
- **Debian 12** Bookworm · minimal, driver from the vendor repository
- **Rocky Linux 9** RHEL-compatible · Slurm, enterprise and HPC stacks
- **Windows Server 2022** Standard · RDP on :3389 · licence billed at our rate · $28/mo licence

### Templates

- Bare OS + driver
- PyTorch 2.7
- TensorFlow 2.18 + JAX 0.5
- Jupyter Lab
- vLLM 0.9 + model
- SGLang 0.4 + model
- Text Generation Inference 3 + model
- Ollama + Open WebUI + model
- ComfyUI
- Stable Diffusion WebUI Forge
- Render node
- Docker + GPU toolkit
- Kubernetes node (k3s)
- Slurm worker

Root over SSH, IPMI console and an API token come with every server. [Access docs](https://dedigpu.com/docs/ssh-and-root-access).

What it is for

## The jobs this card is right for.

- ### Fine-tuning & inference
  LoRA, QLoRA and full fine-tunes on 7B to 70B. vLLM and SGLang templates serve the result from the same server.
  Also a fit. Our first pick here is the [H100 SXM](https://dedigpu.com/gpu/h100-sxm) at $1,134/mo.

Regions

## Deployable in four regions, at the same price.

- **Reykjavík** 18 ms London · 40 ms New York 100% geothermal + hydro
- **Helsinki** 27 ms Frankfurt · 36 ms London 100% wind + hydro
- **Amsterdam** 7 ms Frankfurt · 12 ms London 100% wind
- **Singapore** 38 ms Tokyo · 45 ms Sydney Grid + certified RECs

[Latency tables, power and cooling per region](https://dedigpu.com/regions).

Alternatives

## Cards near this price.

Every one billed the same way. [Compare all 13 side by side](https://dedigpu.com/gpu).

- [MI300X 192 GB HBM3 · CDNA 3 $782 /mo · at cost](https://dedigpu.com/gpu/mi300x)
- [A100 80 GB 80 GB HBM2e · Ampere $654 /mo · at cost](https://dedigpu.com/gpu/a100-80)
- [RTX PRO 6000 96 GB GDDR7 ECC · Blackwell $493 /mo · at cost](https://dedigpu.com/gpu/rtx-pro-6000)
- [H100 SXM 80 GB HBM3 · Hopper $1,134 /mo · at cost](https://dedigpu.com/gpu/h100-sxm)

Guides

## Read before you rent.

- [Economics Renting vs buying an H100: the 36-month math, line by line What an H100 costs to own and run over three years, from the same cost sheet that prices our servers, and the break-even against renting at cost. 2 September 2026 · 8 min read](https://dedigpu.com/guides/renting-vs-buying-an-h100)
- [Training Multi-GPU training: NVLink, InfiniBand, and when one 8× node beats two 4× servers How the interconnect decides training speed: PCIe vs NVLink bandwidth, tensor and pipeline parallelism, InfiniBand between nodes, and how to size a cluster. 2 September 2026 · 8 min read](https://dedigpu.com/guides/multi-gpu-nvlink-infiniband)

Questions

## About the H100 PCIe server.

**How much does a dedicated H100 PCIe server cost per month?**

$810 per card per month for a one-month term, which is the sum of the six lines of its cost sheet rounded up to the dollar: hardware over 36 months, power at our contract rate, rack and cooling, network and IP, spares, operations. A 3, 6 or 12-month term is 3, 6 or 10 % cheaper per month ($729.00 on 12 months). No setup fee, no egress charge, no contract beyond the term.

**Is the H100 PCIe dedicated or shared?**

Dedicated. You rent a physical server with the whole card: no vGPU profile, no time-slicing, no other tenant on the machine. nvidia-smi shows the full 80 GB because you have the full 80 GB. The CPU cores, the RAM and the NVMe are yours too, and so is the IPMI console.

**How many H100 PCIe cards can I have in one server?**

1, 2, 4 or 8, at $810 per card: the chassis share is already in each card's cost, so the price is linear. Cards connect over PCIe 5.0 · NVLink bridge (pairs). For NVLink all-to-all between cards, look at the SXM models.

**Which LLMs fit on an H100 PCIe?**

With the fit rule (parameters × bytes per parameter × 1.2), one card holds up to Qwen3 32B at FP8 and up to Llama 4 Scout · 109B MoE at INT4. An eight-card server (640 GB) holds up to Llama 3.1 405B at FP8. The order form checks the model you name against the server you pick before you pay.

**Which operating systems and templates run on the H100 PCIe?**

Ubuntu 24.04 LTS, Ubuntu 22.04 LTS, Debian 12, Rocky Linux 9, Windows Server 2022. Templates: Bare OS + driver, PyTorch 2.7, TensorFlow 2.18 + JAX 0.5, Jupyter Lab, vLLM 0.9, SGLang 0.4, Text Generation Inference 3, Ollama + Open WebUI, ComfyUI, Stable Diffusion WebUI Forge, Render node, Docker + GPU toolkit, Kubernetes node (k3s), Slurm worker. Serving templates pull the model you name before first boot.

**How long does provisioning take, and can I cancel?**

A single-card server is online in under 5 minutes, an eight-card node in under fifteen minutes, in any of the four regions. The term renews automatically from your balance at the locked price; turn renewal off and the server stops at the end of the paid term, or cancel at any time. No notice period.

**What is the cheapest H100 PCIe rental elsewhere?**

The lowest published monthly price we found for the same card on 2 September 2026 was $1,278 at Hyperstack (reserved) (reserved; hourly rates converted at 730 hours). That is 37 % more than our cost sheet. We re-check every month and print the date.

## Order an H100 PCIe now.

$810 a month at cost, online in under 5 minutes. Create an account, top up in crypto, pick a region.

[Order this server](https://dedigpu.com/signup?gpu=h100-pcie) See the cost sheet