Other · served with ONNX Runtime GenAI · ↓ 0 downloads a month · View on Hugging Face
justinchuby/gemma-4-26b-a4b-it-onnx needs about 65.1 GB of GPU memory. It runs on one Nvidia A800 from $1.13/h right now; best value: RTX PRO 6000 at $1.54/h.
Weights
54 GB
GPU memory needed
about 65.1 GB
Memory · disk
84.4 GB · 143 GB
Licence
gemma
Versions
Smaller versions (8-bit, 4-bit) need less GPU memory and answer a little less precisely.
Deploying ONNX models from the catalog is coming soon. Today, download the files from Hugging Face and upload them in Inference.
Questions
How much GPU memory does gemma-4-26b-a4b-it-onnx need?
About 65.1 GB: 53.58 GB of weights and the runtime's own memory.
What is the cheapest GPU to run gemma-4-26b-a4b-it-onnx?
Right now one Nvidia A800 at $1.13 an hour; RTX PRO 6000 at $1.54 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can gemma-4-26b-a4b-it-onnx run on an RTX 4090?
Not on one: it needs about 65.1 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.
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.