Text generation · served with ONNX Runtime GenAI · ↓ 0 downloads a month · View on Hugging Face
onnx-community/WebWorld-32B-Onnx needs about 79 GB of GPU memory. It runs on one Nvidia A100 from $1.23/h right now; best value: RTX PRO 6000 at $1.52/h.
Weights
66 GB
GPU memory needed
about 79 GB
Memory · disk
102.3 GB · 168 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 WebWorld-32B-Onnx need?
About 79 GB: 65.55 GB of weights and the runtime's own memory.
What is the cheapest GPU to run WebWorld-32B-Onnx?
Right now one Nvidia A100 at $1.23 an hour; RTX PRO 6000 at $1.52 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can WebWorld-32B-Onnx run on an RTX 4090?
Not on one: it needs about 79 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.