How much GPU memory does Qwen2.5-Math-RM-72B need?

About 176.2 GB: 145.55 GB of weights and the runtime's own memory.

What is the cheapest GPU to run Qwen2.5-Math-RM-72B?

No machine on offer right now has enough GPU memory.

Can Qwen2.5-Math-RM-72B run on an RTX 4090?

Not on one: it needs about 176.2 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.

How do I deploy Qwen2.5-Math-RM-72B as an API?

Pick a machine on its GridPup page and press Deploy: GridPup rents the GPU, downloads the model from Hugging Face and serves it at an https address with keys, billed by the hour.

Models / Qwen2.5-Math

Qwen/Qwen2.5-Math-RM-72B

Classification · served with vLLM · ↓ 50.1K downloads a month · View on Hugging Face

Qwen/Qwen2.5-Math-RM-72B needs about 176.2 GB of GPU memory. No machine on offer right now is big enough for it.

Weights: 146 GB
GPU memory needed: about 176.2 GB
Model allows: 4,096 tokens
Memory · disk: 222.3 GB · 201 GB
Architecture: Qwen2ForRewardModel
Licence: other

Hardware and deploy

No machine available right now can serve the model: the largest has 140 GB of GPU memory and the model needs about 176.2 GB.

Endpoint name

billed by the hour; stop it from its page. GridPup rents the machine, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.

Questions

How much GPU memory does Qwen2.5-Math-RM-72B need?: About 176.2 GB: 145.55 GB of weights and the runtime's own memory.
What is the cheapest GPU to run Qwen2.5-Math-RM-72B?: No machine on offer right now has enough GPU memory.
Can Qwen2.5-Math-RM-72B run on an RTX 4090?: Not on one: it needs about 176.2 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.
How do I deploy Qwen2.5-Math-RM-72B as an API?: Pick a machine on its GridPup page and press Deploy: GridPup rents the GPU, downloads the model from Hugging Face and serves it at an https address with keys, billed by the hour.

Loading…