TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Suggest a low-end hosting provider with GPU

6 pointsby backend-dev-338 months ago
I want to do zero-shot text classification with this model [1] or with something similar (Size of the model: 711 MB &quot;model.safetensors&quot; file, 1.42 GB &quot;model.onnx&quot; file ) It works on my dev machine with 4GB GPU. Probably will work on 2GB GPU too.<p>Is there some hosting provider for this?<p>My app is doing batch processing, so I will need access to this model few times per day. Something like this: start processing do some text classification stop processing Imagine I will do this procedure... 3 times per day. I don&#x27;t need this model the rest of the time. Probably can start&#x2F;stop some machine per API to save costs...<p>[1] https:&#x2F;&#x2F;huggingface.co&#x2F;MoritzLaurer&#x2F;roberta-large-zeroshot-v2.0-c

1 comment

backend-dev-337 months ago
I was just told about this thing: <a href="https:&#x2F;&#x2F;aws.amazon.com&#x2F;ec2&#x2F;instance-types&#x2F;g4&#x2F;" rel="nofollow">https:&#x2F;&#x2F;aws.amazon.com&#x2F;ec2&#x2F;instance-types&#x2F;g4&#x2F;</a><p>one NVIDIA T4 GPU, 16 GB RAM, and, this is an EC2 instance, it means &quot;install anything&quot; all this for $0.526 &#x2F;Hour<p>do you see any hidden gotchas?