gpuendpoints.com
Market/Text Generation WebUI
Language models

Text Generation WebUI

Chat and complete with LLaMA, Mistral, and similar models. GPTQ and AWQ supported.

Details

Image
pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
Ports
7860/http, 22/tcp
Setup
3-5 minutes
Difficulty
intermediate
Features
Chat UI, GPTQ / AWQ, LoRA adapters, HTTP API
Compatible GPUs
RTX 3090
24GB GDDR6X
budget$0.26 / hr
RTX 4090
24GB GDDR6X
standard$0.44 / hr
RTX A5000
24GB GDDR6
standard$0.36 / hr
RTX A6000
48GB GDDR6
premium$0.49 / hr
L40
48GB GDDR6
premium$0.79 / hr
A100 40GB
40GB HBM2e
premium$1.29 / hr
A100 80GB
80GB HBM2e
enterprise$1.89 / hr
H100 80GB
80GB HBM3
enterprise$2.99 / hr
Start
locked

Holders of 10,000 $GPU start against the treasury-funded cluster. Sessions are capped at 1 hour. Everyone else can read specs.

Runtime 1 hour (fixed)
App Text Generation WebUI
Image pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04
Ports 7860/http,22/tcp

Connect a wallet on Robinhood Chain.