*[DediGPU](https://dedigpu.com/) — Markdown mirror of [https://dedigpu.com/gpu/a100-80](https://dedigpu.com/gpu/a100-80) · 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 · Ampere

# Dedicated NVIDIA A100 SXM4 80 GB server, $654 a month.

The whole card — 80 GB of HBM2e at 2.04 TB/s — with 16 dedicated vCPU, 128 GB of RAM and 1 TB of NVMe, on a 100 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, full NVLink 3 · 600 GB/s
- 4 regions, same price
- No setup fee, no KYC, crypto balance
- 99.9% SLA credited ×10

- **80 GB** HBM2e per card
- **2.04 TB/s** memory bandwidth
- **600 GB/s** NVLink 3
- **100 Gbit/s** port, $0 egress
- **400 W** board power, in the cost sheet

The cost sheet

## What an A100 80 GB 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 $11,000 card + $8,750 chassis share, over 36 months $548.61
- Power 353 kWh at $0.052 · 600 W, 70% load, PUE 1.15 $18.33
- Rack & cooling HGX baseboard, liquid-assisted $45.00
- Network & IP transit share, one IPv4, port $9.00
- Spares & failures 2% of the card price per year $18.33
- Operations monitoring, on-call, provisioning $14.00
- Total rounded up to the next dollar $653.28 → $654

Cheapest published price we found for the same card: $694 per month at Hyperstack (reserved) (reserved), checked 2 September 2026 — 6% 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. Every count sits on the same 8-way baseboard with the full fabric between your cards.

| Server | GPU memory | CPU | RAM | NVMe | Network | Per month | 12-month rate |  |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| **1× A100 80 GB** | 80 GB | 16 vCPU | 128 GB | 1 TB | 100 Gbit/s | $654 | $588.60 | [Order](https://dedigpu.com/signup?gpu=a100-80&n=1) |
| **2× A100 80 GB** | 160 GB | 32 vCPU | 256 GB | 2 TB | 100 Gbit/s | $1,308 | $1,177.20 | [Order](https://dedigpu.com/signup?gpu=a100-80&n=2) |
| **4× A100 80 GB** | 320 GB | 64 vCPU | 512 GB | 4 TB | 100 Gbit/s | $2,616 | $2,354.40 | [Order](https://dedigpu.com/signup?gpu=a100-80&n=4) |
| **8× A100 80 GB** | 640 GB | 128 vCPU | 1024 GB | 8 TB | 100 Gbit/s + IB | $5,232 | $4,708.80 | [Order](https://dedigpu.com/signup?gpu=a100-80&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 | $654.00 | $654.00 | — |
| **3 months** | −3 % | $634.38 | $1,903.14 | $58.86 |
| **6 months** | −6 % | $614.76 | $3,688.56 | $235.44 |
| **12 months** | −10 % | $588.60 | $7,063.20 | $784.80 |

For one A100 80 GB; 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 A100 SXM4 80 GB
- **Architecture:** Ampere
- **GPU memory:** 80 GB HBM2e
- **Memory bandwidth:** 2.04 TB/s
- **Interconnect:** NVLink 3 · 600 GB/s
- **Form factor:** SXM module on an HGX 8-GPU baseboard
- **Board power:** 400 W
- **CPU per card:** 16 dedicated vCPU
- **System RAM per card:** 128 GB ECC
- **Local NVMe per card:** 1 TB
- **Network:** 100 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× A100 80 GB.

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

### 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.

- ### LLM training & pre-training
  8-GPU NVLink nodes with 3.2 Tbps InfiniBand between them. Checkpoints land on local NVMe at 14 GB/s.
  Also a fit. Our first pick here is the [B200](https://dedigpu.com/gpu/b200) at $1,408/mo.
- ### 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)
- [H100 PCIe 80 GB HBM2e · Hopper $810 /mo · at cost](https://dedigpu.com/gpu/h100-pcie)
- [RTX PRO 6000 96 GB GDDR7 ECC · Blackwell $493 /mo · at cost](https://dedigpu.com/gpu/rtx-pro-6000)
- [L40S 48 GB GDDR6 ECC · Ada Lovelace $356 /mo · at cost](https://dedigpu.com/gpu/l40s)

Guides

## Read before you rent.

- [Economics Dedicated GPU server vs GPU cloud: what the hourly price hides The lines that do not appear on an hourly GPU price: storage that keeps billing, egress, idle hours, pre-emption, shared hosts. And when the cloud is still the right call. 2 September 2026 · 7 min read](https://dedigpu.com/guides/dedicated-gpu-server-vs-gpu-cloud)

Questions

## About the A100 80 GB server.

**How much does a dedicated A100 80 GB server cost per month?**

$654 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 ($588.60 on 12 months). No setup fee, no egress charge, no contract beyond the term.

**Is the A100 80 GB 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 A100 80 GB cards can I have in one server?**

1, 2, 4 or 8, at $654 per card: the chassis share is already in each card's cost, so the price is linear. Every count sits on the same 8-way baseboard with the full NVLink 3 · 600 GB/s fabric between your cards; eight-card nodes add 3.2 Tbps InfiniBand for clusters of 16 to 512 cards.

**Which LLMs fit on an A100 80 GB?**

With the fit rule (parameters × bytes per parameter × 1.2), one card holds up to Qwen3 32B at INT8 and up to Llama 4 Scout · 109B MoE at INT4. An eight-card server (640 GB) holds up to Llama 3.1 405B at INT8. The order form checks the model you name against the server you pick before you pay.

**Which operating systems and templates run on the A100 80 GB?**

Ubuntu 24.04 LTS, Ubuntu 22.04 LTS, Debian 12, Rocky Linux 9. 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 A100 80 GB rental elsewhere?**

The lowest published monthly price we found for the same card on 2 September 2026 was $694 at Hyperstack (reserved) (reserved; hourly rates converted at 730 hours). That is 6 % more than our cost sheet. We re-check every month and print the date.

## Order an A100 80 GB now.

$654 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=a100-80) See the cost sheet