ML Inference

AI+SRV

Free AI inference and database hosting

For master's and postgraduate students only

ML INFERENCE SQL DATABASE FILE STORAGE

ML Inference

You can upload file and run the inference of your model in GGUF format on LLama CPP or it fork server with permanent API web address.

Version: b6829
Access: via your-project-name.ai.ephz.ch:1234
Model size: limited by server hardware
Storage: SSD PCIe with RAM buffer

1

Unlimited size

Model size limit RAM and VRAM capasity only. Fast startup from SSD.

2

Open access

Only open web access is provided.

3

Stable working

There is no any automatic shutdown during the agreed guaranteed operation period.

4

Free using

Free use for authors and end users.

Intel Xeon 2.4 Ghz

A-1

10 CPU cores
64 Gb RAM

VRAM 8 Gb total
1 card x 8 Gb VRAM
NVIDIA QUADRO
RTX 4000

REQUEST

Intel Xeon 2.4 GHz

A-2

20 CPU cores
128 Gb RAM

VRAM 16 Gb total
2 cards x 8 Gb VRAM
NVIDIA QUADRO
RTX 4000

REQUEST

Intel Xeon 2.4 GHz

A-3

30 CPU cores
192 Gb RAM

VRAM 24 Gb total
3 cards x 8 Gb VRAM
NVIDIA QUADRO
RTX 4000

BUSY

AI+SRV

Free AI inference and database hosting

ML Inference

You can upload file and run the inference of your model in GGUF format on LLama CPP or it fork server with permanent API web address.

Version: b6829
Access: via your-project-name.ai.ephz.ch:1234
Model size: limited by server hardware
Storage: SSD PCIe with RAM buffer

1

Unlimited size

2

Open access

3

Stable working

4

Free using

A-1

A-2

A-3

CONTACT FORM

Just add your ML project description and send
without any doubt :)

AI+SRV

Free AI inference and database hosting

ML Inference

You can upload file and run the inference of your model in GGUF format on LLama CPP or it fork server with permanent API web address.Version: b6829Access: via your-project-name.ai.ephz.ch:1234Model size: limited by server hardwareStorage: SSD PCIe with RAM buffer

1

Unlimited size

2

Open access

3

Stable working

4

Free using

A-1

A-2

A-3

CONTACT FORM

Just add your ML project description and send without any doubt :)

You can upload file and run the inference of your model in GGUF format on LLama CPP or it fork server with permanent API web address.

Version: b6829
Access: via your-project-name.ai.ephz.ch:1234
Model size: limited by server hardware
Storage: SSD PCIe with RAM buffer

Just add your ML project description and send
without any doubt :)