Text generation · served with ONNX Runtime GenAI · ↓ 23 downloads a month · View on Hugging Face
wekkel/Qwen3-14B-Instruct-DirectML-INT4 needs about 13.7 GB of GPU memory. It runs on one RTX A4000 from $0.11/h right now; best value: RTX 5070 Ti at $0.21/h.
Weights
9.4 GB
GPU memory needed
about 13.7 GB
Memory · disk
18.2 GB · 50 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 Qwen3-14B-Instruct-DirectML-INT4 need?
About 13.7 GB: 9.45 GB of weights and the runtime's own memory.
What is the cheapest GPU to run Qwen3-14B-Instruct-DirectML-INT4?
Right now one RTX A4000 at $0.11 an hour; RTX 5070 Ti at $0.21 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can Qwen3-14B-Instruct-DirectML-INT4 run on an RTX 4090?
Yes: it needs about 13.7 GB and an RTX 4090 has 24 GB.