How much GPU memory does lille-130m-instruct need?

About 1.4 GB: 0.3 GB of weights and the runtime's own memory.

What is the cheapest GPU to run lille-130m-instruct?

Right now one Quadro P4000 at $0.07 an hour; RTX 5090 at $0.65 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.

Can lille-130m-instruct run on an RTX 4090?

Yes: it needs about 1.4 GB and an RTX 4090 has 24 GB.

Models / lille

Nikity/lille-130m-instruct

Text generation · served with ONNX Runtime · ↓ 777 downloads a month · View on Hugging Face

Nikity/lille-130m-instruct needs about 1.4 GB of GPU memory. It runs on one Quadro P4000 from $0.07/h right now; best value: RTX 5090 at $0.65/h.

These ONNX files are an export for running in a browser: GridPup serves them as tensors in and out, not as a chat. For chat, pick the same model in its original form (served with vLLM).

Weights: 300 MB
GPU memory needed: about 1.4 GB
Memory · disk: 8 GB · 30 GB
Licence: apache-2.0

Hardware and deploy

Deploying ONNX models from the catalog is coming soon. Today, download the files from Hugging Face and upload them in Inference.

Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.

Questions

How much GPU memory does lille-130m-instruct need?: About 1.4 GB: 0.3 GB of weights and the runtime's own memory.
What is the cheapest GPU to run lille-130m-instruct?: Right now one Quadro P4000 at $0.07 an hour; RTX 5090 at $0.65 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can lille-130m-instruct run on an RTX 4090?: Yes: it needs about 1.4 GB and an RTX 4090 has 24 GB.

Loading…