NVIDIA · Ada Lovelace

Rent RTX 6000 Ada

NVIDIA RTX 6000 Ada Generation, 48 GB.RenderingVirtual desktopsgeneral ml

Full price from

€0.62

in stock, per GPU-hour, as 1×

Spot from

—

in stock, per GPU-hour

Offers in stock

1 of 2

full price or spot

Providers in stock

1 of 2

full price or spot

Offers (2)

Cheapest in stock

NosanaIn stock · 1 freeStart right away

1× RTX 6000 Ada48 GB VRAM

Nosana network, hosts worldwide

Details

Stock and price checked 16 min ago.

Self-service: you start it yourself, with no order or sales contact.

nvidia-6000-ada

Full price

€0.62

per hour, whole instance, 1 GPU

View offer

kyberioVerified PartnerNo stock dataPrice not verifiedOn requestMinimum 12 months

1× RTX 6000 Ada48 GB VRAM

Germany · 24 vCPU · 2× 1.92 TB NVMe

Details

Stock and price checked 16 min ago.

You have to contact their sales team.

dedicated-rtx-6000-ada-monthly-from-969

Full price

€1.33

per hour, whole instance, 1 GPU

View offer

Price and availability history

Price per GPU-hour

Excluding VAT.

Providers with stock

Each provider counts once. Full price and spot are separate.

Share of offers in stock

Full price. Offers we can't say are really sold there are left out until they've been in stock once.

Units free

Only providers that report a number. Each line is one provider and one server size, because their counts cover different things and can't be added up. Providers that only say yes or no are under Stock by provider.

Stock by provider

In stock, yes or no, for every provider selling this GPU. A filled band means in stock: green at full price, orange as spot.

NosanaIn stock

Reports a number

kyberioNo stock data

No stock data shown

In stock as

The server sizes you can rent right now.

Nosana: 1×

Using several together

Can't be linked. This GPU has no NVLink, so several in one server only talk over PCIe at up to 64 GB/s. Each card keeps its own 48 GB. That suits running a separate job on each card. Splitting one model across them works, but slowly.

Specifications

Datasheet memory bandwidth 960 GB/s; NVIDIA architecture whitepaper lists 1008 GB/s. No NVLink. fp64Tflops is derived: NVIDIA states AD102 FP64 is 1/64th of FP32 (91.1 / 64). pcieBandwidthGBs is PCIe 4.0 x16, 64 GB/s per NVIDIA. FP16, BF16 and INT8 are with sparsity.

Memory

VRAM: 48 GB
Memory type: GDDR6
Memory bandwidth How fast the GPU reaches its memory. Often limits LLM speed: 960 GB/s
Bus width: 384 bit
ECC memory Detects and corrects memory errors: Yes

Compute

FP64 Speed at 64-bit precision, used for scientific simulation: 1.42 TFLOPS
FP32 Speed at 32-bit precision: 91.1 TFLOPS
FP16 Speed at 16-bit precision: 728.4 TFLOPS
BF16 16-bit AI format. Standard for training and full-quality inference: 728.4 TFLOPS
FP8 8-bit AI format. About half the memory of BF16, slightly lower quality: 1,457 TFLOPS
INT8 8-bit integer speed, used by quantized models: 1,457 TOPS
FP8 support: Yes
FP4 support: No
Transformer Engine Hardware that speeds up FP8 and FP4: Yes
Compute cores: 18,176

Multi-GPU and connectivity

NVSwitch Lets every GPU in a server talk to every other at full speed: No
PCIe generation: 4
PCIe lanes: 16
PCIe bandwidth: 64 GB/s

Sharing and security

MIG partitioning Splits one GPU into several isolated smaller GPUs: No
Max MIG instances: 0
vGPU: Yes
Confidential computing: No

Hardware

Architecture: Ada Lovelace
Launch year: 2022
Process node: TSMC 4N
Transistors: 76.3 billion
Die size: 608.5 mm²
Power (TDP) Maximum power draw: 300 W
Cooling: active

Video

NVENC engines: 3
NVDEC engines: 3
AV1 encode: Yes
AV1 decode: Yes

Sources (47)