NVIDIA · Ampere
Norway · 56 vCPU · 215 GB RAM · 100GB root + 1200GB ephemeral
Stock and price checked 16 min ago.
You start it yourself once there is stock.
This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.
n3-RTX-A4000x10
Norway · 4 vCPU · 21 GB RAM · 100GB root
Stock and price checked 16 min ago.
You start it yourself once there is stock.
n3-RTX-A4000x1
Norway · 8 vCPU · 43 GB RAM · 100GB root + 100GB ephemeral
Stock and price checked 16 min ago.
You start it yourself once there is stock.
This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.
n3-RTX-A4000x2
Norway · 16 vCPU · 86 GB RAM · 100GB root + 400GB ephemeral
Stock and price checked 16 min ago.
You start it yourself once there is stock.
This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.
n3-RTX-A4000x4
Norway · 32 vCPU · 172 GB RAM · 100GB root + 800GB ephemeral
Stock and price checked 16 min ago.
You start it yourself once there is stock.
This GPU has no fast GPU-to-GPU link. These are separate cards: good for separate jobs, slow for one model split across them.
n3-RTX-A4000x8
Nosana network, hosts worldwide
Stock and price checked 16 min ago.
You start it yourself once there is stock.
nvidia-a4000
Excluding VAT.
Each provider counts once. Full price and spot are separate.
Full price. Offers we can't say are really sold there are left out until they've been in stock once.
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.
In stock, yes or no, for every provider selling this GPU. A filled band means in stock: green at full price, orange as spot.
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 16 GB. That suits running a separate job on each card. Splitting one model across them works, but slowly.
Single-slot; no NVLink. memoryDataRateGbps is derived (448 GB/s x 8 / 256 bits). pcieBandwidthGBs is PCIe 4.0 x16, 64 GB/s per NVIDIA. Datasheet gives 153.4 Tensor TFLOPS without naming the precision, so FP16/BF16/INT8 stay null.