Deploy Popular AI/ML Models At The Lowest Cost

Use ready-to deploy Recipes of models like Stable Diffusion, Llama 7B & Whisper.
Sign up, go to Recipe Marketplace, choose model & GPUs and start running.
Get to production fast on the lowest priced cloud in just a few clicks.

Language learning model - LLM - Llama 7b
Llama 7b
meta-llama-7b
$0.282 / hour

Llama - 7b

Llama is an auto-regressive learning language model, created by Meta

Intended Uses & Limitations

Llama is intended to be used primarily for research purposes, and may not be fit for down-stream applications without additional filtering or checks.

Hardware

  • vCPU - 4x
  • RAM - 16GB
  • GPU - RTX 3090 (24GB)
Alpaca 7b language learning model gpu
Alpaca 7b
stanford-alpaca-7b
$0.282 / hour

Alpaca - 7b

Alpaca is a fine-tuned variant of Alpaca 7B from Meta, and is designed for instruction following.

Intended Uses & Limitations

This model has not yet been fine-tuned to be safe and harmless, and caution is recommended for any responses given.

Hardware

  • vCPU - 4x
  • RAM - 16GB
  • GPU - RTX 3090 (24GB)
Stable diffusion 1.4 gpu benchmark
Stable Diffusion 1.4
stable-diffusion-1-4-base
$0.104 / hour

Stable Diffusion 1.4

Stable Diffusion 1.4 is a model that, via text prompts, can be used to generate or modify images. Stable Diffusion 1.4 is trained for creation of realistic images of all types, and is not trained for a specific art style or image generation style.

Intended Uses & Limitations

Content generated by this model should not be used to harm or discriminate.

Hardware

  • vCPU - 2x
  • RAM - 16GB
  • GPU - RTX 3060 (12GB)
anythingv4 stable diffusion deployment gpu
Anything v4.0
stable-diffusion-andite-anything-v4-0
$0.104 / hour

Anything v4.0

Anything is a Stable Diffusion model that, via text prompts, can be used to generate or modify images. Anything v4.0 is trained for creation of highly detailed, high quality anime-style images.

Intended Uses & Limitations

Content generated by this model should not be used to harm or discriminate.

Hardware

  • vCPU - 2x
  • RAM - 16GB
  • GPU - RTX 3060 (12GB)
Code-llama-7b deployment on gpu
Code Llama 7B
meta-code-llama-7b
$0.282 / hour

Code Llama 7B

Llama is an auto-regressive learning language model, created by Meta. This variant of the model is designed to finish writing software code prompts.

Intended Uses & Limitations

Llama is intended to be used primarily for research purposes, and may not be fit for down-stream applications without additional filtering or checks.

Hardware

  • vCPU - 4x
  • RAM - 16GB
  • GPU - RTX 3090 (24GB)
MPT-7B-Base
mosaicml-mpt-7b-base
$0.232 / hour

MPT-7B-Base

MPT-7B is a decoder style transformer trained on 1 Trillion tokens of English language text by MosaicML. This is the 7B-Base variant of the model

Intended Uses & Limitations

This model is not intended for deployment without finetuning or guardrails for human interaction.

Hardware

  • vCPU - 4x
  • RAM - 16GB
  • GPU - RTX 3080 Ti (12GB)
GPT2- model deployment on gpu cloud
GPT2
openai-gpt2
$0.024 / hour

GPT2

GPT2 is a transformers model that was pretrained on a large volume of raw English text with no human labelling. This model allows you to generate text based on a prompt, based on data from the training model. This is the smaller available model, with 124M parameters.

Intended Uses & Limitations

GPT2 can be used to expand a starter text prompt. As GPT2 has been trained on unfiltered content from the internet, it may contain biased and incorrect information. Content generated by GPT2 should be filtered and corrected by downstream studying.

Hardware

  • vCPU - 4x
  • RAM - 8GB
  • GPU - N/A
 MPT 7b storywriter deployment on salad gpu cloud
MPT-7B-Storywriter
mosaicml-mpt-7b-storywriter
$0.232 / hour

MPT-7B-Storywriter

MPT-7B is a decoder style transformer trained on 1 Trillion tokens of English language text by MosaicML. This is the 7B-Storywriter variant of the model

Intended Uses & Limitations

This model is not intended for deployment without finetuning or guardrails for human interaction.

Hardware

  • vCPU - 4x
  • RAM - 16GB
  • GPU - RTX 3080 Ti (12GB)