*[DediGPU](https://dedigpu.com/) — Markdown mirror of [https://dedigpu.com/gpu/b200](https://dedigpu.com/gpu/b200) · 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 · Blackwell *Flagship*

# Dedicated NVIDIA B200 SXM6 server, $1,408 a month.

The whole card — 180 GB of HBM3e at 8 TB/s — with 28 dedicated vCPU, 224 GB of RAM and 2 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 5 · 1.8 TB/s
- 4 regions, same price
- No setup fee, no KYC, crypto balance
- 99.9% SLA credited ×10

- **180 GB** HBM3e per card
- **8 TB/s** memory bandwidth
- **1.8 TB/s** NVLink 5
- **100 Gbit/s** port, $0 egress
- **1000 W** board power, in the cost sheet

The cost sheet

## What a B200 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 $36,000 card + $8,750 chassis share, over 36 months $1,243.06
- Power 705 kWh at $0.052 · 1200 W, 70% load, PUE 1.15 $36.67
- 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 $60.00
- Operations monitoring, on-call, provisioning $14.00
- Total rounded up to the next dollar $1,407.72 → $1,408

Cheapest published price we found for the same card: $3,723 per month at Hyperstack (reserved) (reserved), checked 2 September 2026 — 62% 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× B200** | 180 GB | 28 vCPU | 224 GB | 2 TB | 100 Gbit/s | $1,408 | $1,267.20 | [Order](https://dedigpu.com/signup?gpu=b200&n=1) |
| **2× B200** | 360 GB | 56 vCPU | 448 GB | 4 TB | 100 Gbit/s | $2,816 | $2,534.40 | [Order](https://dedigpu.com/signup?gpu=b200&n=2) |
| **4× B200** | 720 GB | 112 vCPU | 896 GB | 8 TB | 100 Gbit/s | $5,632 | $5,068.80 | [Order](https://dedigpu.com/signup?gpu=b200&n=4) |
| **8× B200** | 1440 GB | 224 vCPU | 1792 GB | 16 TB | 100 Gbit/s + IB | $11,264 | $10,137.60 | [Order](https://dedigpu.com/signup?gpu=b200&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 | $1,408.00 | $1,408.00 | — |
| **3 months** | −3 % | $1,365.76 | $4,097.28 | $126.72 |
| **6 months** | −6 % | $1,323.52 | $7,941.12 | $506.88 |
| **12 months** | −10 % | $1,267.20 | $15,206.40 | $1,689.60 |

For one B200; 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 B200 SXM6
- **Architecture:** Blackwell
- **GPU memory:** 180 GB HBM3e
- **Memory bandwidth:** 8 TB/s
- **Interconnect:** NVLink 5 · 1.8 TB/s
- **Form factor:** SXM module on an HGX 8-GPU baseboard
- **Board power:** 1000 W
- **CPU per card:** 28 dedicated vCPU
- **System RAM per card:** 224 GB ECC
- **Local NVMe per card:** 2 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× B200.

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 180 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.
  Our recommendation for this workload.

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).

- [H200 141 GB HBM3e · Hopper $1,252 /mo · at cost](https://dedigpu.com/gpu/h200)
- [H100 SXM 80 GB HBM3 · Hopper $1,134 /mo · at cost](https://dedigpu.com/gpu/h100-sxm)
- [B300 *Flagship* 288 GB HBM3e · Blackwell Ultra $1,762 /mo · at cost](https://dedigpu.com/gpu/b300)
- [H100 PCIe 80 GB HBM2e · Hopper $810 /mo · at cost](https://dedigpu.com/gpu/h100-pcie)

Guides

## Read before you rent.

- [Inference How much VRAM do you need to run an LLM? Every size, every precision A single rule, a table for eleven popular models from 8B to 671B at BF16, FP8, INT8 and INT4, and the cheapest dedicated server that fits each one. 2 September 2026 · 9 min read](https://dedigpu.com/guides/how-much-vram-to-run-an-llm)
- [Hardware H100 vs H200 vs B200 vs B300: which one to rent in 2026 Memory, bandwidth, NVLink and price per month of the four NVIDIA data-centre generations on the catalogue, and a plain answer for training, fine-tuning and inference. 2 September 2026 · 8 min read](https://dedigpu.com/guides/h100-vs-h200-vs-b200-vs-b300)
- [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)

Questions

## About the B200 server.

**How much does a dedicated B200 server cost per month?**

$1,408 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 ($1,267.20 on 12 months). No setup fee, no egress charge, no contract beyond the term.

**Is the B200 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 180 GB because you have the full 180 GB. The CPU cores, the RAM and the NVMe are yours too, and so is the IPMI console.

**How many B200 cards can I have in one server?**

1, 2, 4 or 8, at $1,408 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 5 · 1.8 TB/s fabric between your cards; eight-card nodes add 3.2 Tbps InfiniBand for clusters of 16 to 512 cards.

**Which LLMs fit on a B200?**

With the fit rule (parameters × bytes per parameter × 1.2), one card holds up to Mixtral 8x22B · 141B MoE at FP8 and up to Qwen3 235B-A22B · MoE at INT4. An eight-card server (1440 GB) holds up to DeepSeek-V3 / R1 · 671B MoE 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 B200?**

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 B200 rental elsewhere?**

The lowest published monthly price we found for the same card on 2 September 2026 was $3,723 at Hyperstack (reserved) (reserved; hourly rates converted at 730 hours). That is 62 % more than our cost sheet. We re-check every month and print the date.

## Order a B200 now.

$1,408 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=b200) See the cost sheet