NVIDIA · Ada Lovelace

Rent RTX 4060

NVIDIA GeForce RTX 4060, 8 GB.inference smallRendering

Full price from

—

in stock, per GPU-hour

Spot from

—

in stock, per GPU-hour

Offers in stock

0 of 1

full price or spot

Providers in stock

0 of 1

full price or spot

Offers (1)

NosanaSold outSelf-service

1× RTX 40608 GB VRAM

Nosana network, hosts worldwide

Details

Stock and price checked 15 min ago.

You start it yourself once there is stock.

nvidia-4060

Full price

€0.06

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.

NosanaSold out

Reports a number

Using several together

Can't be linked. This GPU has no NVLink, so several in one server only talk over PCIe. Each card keeps its own 8 GB. That suits running a separate job on each card. Splitting one model across them works, but slowly.

Specifications

Consumer card. fp32Tflops is derived: 3072 CUDA cores x 2 FP32 operations per clock x 2.46 GHz boost = 15.1; NVIDIA's compare page rounds this to 15 Shader TFLOPS. FP8, FP16, BF16 and INT8 stay null: NVIDIA lists 242 AI TOPS for this card without naming the precision. fp64Tflops stays null because NVIDIA states the 1/64th FP64 ratio only for AD102. rtCores is derived: 3072 cores / 128 per SM = 24 SMs, one RT Core per SM as in NVIDIA's Ada tables. memoryDataRateGbps, memoryBandwidthGBs (128 bits x 17 Gbps / 8), transistorsBillion, dieSizeMm2 and pcieLanes are from TechPowerUp's board database. cooling stays null because NVIDIA states card dimensions vary by manufacturer and lists no Founders Edition; partner coolers vary. No NVLink/SLI.

Memory

VRAM: 8 GB
Memory type: GDDR6
Memory bandwidth How fast the GPU reaches its memory. Often limits LLM speed: 272 GB/s
Bus width: 128 bit

Compute

FP32 Speed at 32-bit precision: 15.1 TFLOPS
FP8 support: Yes
FP4 support: No
Transformer Engine Hardware that speeds up FP8 and FP4: Yes
Compute cores: 3,072

Multi-GPU and connectivity

NVSwitch Lets every GPU in a server talk to every other at full speed: No
PCIe generation: 4
PCIe lanes: 8

Sharing and security

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

Hardware

Architecture: Ada Lovelace
Launch year: 2023
Process node: TSMC 4N
Transistors: 18.9 billion
Die size: 159 mm²
Power (TDP) Maximum power draw: 115 W

Video

NVENC engines: 1
NVDEC engines: 1
AV1 encode: Yes
AV1 decode: Yes

Sources (35)