NVIDIA · Blackwell Ultra Flagship
Dedicated NVIDIA B300 SXM6 server, $1,762 a month.
The whole card — 288 GB of HBM3e at 8 TB/s — with 32 dedicated vCPU, 288 GB of RAM and 3 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
- 288 GBHBM3e per card
- 8 TB/smemory bandwidth
- 1.8 TB/sNVLink 5
- 100 Gbit/sport, $0 egress
- 1000 Wboard power, in the cost sheet
The cost sheet
What a B300 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.
- Hardware$48,000 card + $8,750 chassis share, over 36 months$1,576.39
- Power705 kWh at $0.052 · 1200 W, 70% load, PUE 1.15$36.67
- Rack & coolingHGX baseboard, liquid-assisted$45.00
- Network & IPtransit share, one IPv4, port$9.00
- Spares & failures2% of the card price per year$80.00
- Operationsmonitoring, on-call, provisioning$14.00
- Totalrounded up to the next dollar$1,761.06 → $1,762
Cheapest published price we found for the same card: $5,840 per month at Latitude.sh (8× node) (dedicated), checked 2 September 2026 — 70% 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.
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× B300 | 288 GB | 32 vCPU | 288 GB | 3 TB | 100 Gbit/s | $1,762 | $1,585.80 | Order |
| 2× B300 | 576 GB | 64 vCPU | 576 GB | 6 TB | 100 Gbit/s | $3,524 | $3,171.60 | Order |
| 4× B300 | 1152 GB | 128 vCPU | 1152 GB | 12 TB | 100 Gbit/s | $7,048 | $6,343.20 | Order |
| 8× B300 | 2304 GB | 256 vCPU | 2304 GB | 24 TB | 100 Gbit/s + IB | $14,096 | $12,686.40 | Order |
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.
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 | $1,762.00 | $1,762.00 | — |
| 3 months | −3 % | $1,709.14 | $5,127.42 | $158.58 |
| 6 months | −6 % | $1,656.28 | $9,937.68 | $634.32 |
| 12 months | −10 % | $1,585.80 | $19,029.60 | $2,114.40 |
For one B300; multiply by the card count. Renewal takes the same term at the same rate. How renewals, grace and suspension work.
Specifications
Per card, before you multiply.
- GPU
- NVIDIA B300 SXM6
- Architecture
- Blackwell Ultra
- GPU memory
- 288 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
- 32 dedicated vCPU
- System RAM per card
- 288 GB ECC
- Local NVMe per card
- 3 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× B300.
Memory needed = parameters × bytes per parameter × 1.2 (KV cache and runtime). Change the card count above and the table follows. The full guide.
| 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 288 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.
Operating systems
- Ubuntu 24.04 LTSKernel 6.8 · the default for every template
- Ubuntu 22.04 LTSKernel 5.15 HWE · for stacks pinned to CUDA 11.8 / 12.1
- Debian 12Bookworm · minimal, driver from the vendor repository
- Rocky Linux 9RHEL-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.
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 at $1,408/mo.
Regions
Deployable in four regions, at the same price.
Reykjavík18 ms London · 40 ms New York100% geothermal + hydro
Helsinki27 ms Frankfurt · 36 ms London100% wind + hydro
Amsterdam7 ms Frankfurt · 12 ms London100% wind
Singapore38 ms Tokyo · 45 ms SydneyGrid + certified RECs
Guides
Read before you rent.
Questions
About the B300 server.
How much does a dedicated B300 server cost per month?
$1,762 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 ($1,585.80 on 12 months). No setup fee, no egress charge, no contract beyond the term.
Is the B300 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 288 GB because you have the full 288 GB. The CPU cores, the RAM and the NVMe are yours too, and so is the IPMI console.
How many B300 cards can I have in one server?
1, 2, 4 or 8, at $1,762 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 B300?
With the fit rule (parameters × bytes per parameter × 1.2), one card holds up to Qwen3 235B-A22B · MoE at FP8 and up to Llama 3.1 405B at INT4. An eight-card server (2304 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 B300?
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 B300 rental elsewhere?
The lowest published monthly price we found for the same card on 2 September 2026 was $5,840 at Latitude.sh (8× node) (dedicated; hourly rates converted at 730 hours). That is 70 % more than our cost sheet. We re-check every month and print the date.
Order a B300 now.
$1,762 a month at cost, online in under 5 minutes. Create an account, top up in crypto, pick a region.