Run Mistral 7B v0.3
Ready in about 90 seconds. No install, no setup. From $0.45 per hour.
What it does
Mistral 7B is a similar size and capability to Llama 3.1 8B, and trains just as easily on one card.
The reason to pick it is the license. It is Apache 2.0, so the model you train is yours to ship in a product with no naming requirements, no user thresholds, and no obligations.
If you are fine-tuning something that will end up inside a product you sell, start here rather than with Llama.
What you can ask it
1,200 examples of your product documentation voice.
You get backA model you can ship inside your own product with no license conditions.
Your internal terminology and how it should be used.
You get backA model that stops translating your jargon into generic language.
Examples of a structured output format you need every time.
You get backA model that produces valid output without a long prompt.
Your setup
We run this on an RTX 4090. A LoRA fine-tune on a thousand examples takes about 35 minutes, which is roughly $0.26. $0.45 per hour, billed by the minute.
Why this card?
Same reasoning as Llama 3.1 8B. LoRA training on a 7 billion parameter model needs about 15GB with a reasonable batch size, and a 24GB card covers that with headroom for longer training examples. Going larger buys you a bigger batch size and a modestly shorter run, which does not pay for itself at this scale.
- Memory
- 24GB
- Speed
- about 2 seconds per example
- Rate
- $0.45/hr
What will it cost you?
Billed by the minute on a RTX 4090 at $0.45 per hour. A batch job shuts the GPU off when the last example is done, so this is the whole cost.
Two ways to run it
Click and use it
JupyterLab with the training stack ready to go.
Get early access Best for exploring.Hand us the whole pile
Spreadsheet of examples in, trained adapter out.
Join the list Best for volume. The GPU shuts off automatically when it is done.Model facts
| Parameters | 7.3B |
|---|---|
| License | Apache 2.0 |
| Memory required | 15GB minimum for LoRA |
| Base model | Trained from scratch by Mistral AI |
| Publisher | Mistral AI |
| Recommended hardware | RTX 4090, 24GB |
| Hugging Face | mistralai/Mistral-7B-Instruct-v0.3 |
Want Mistral 7B v0.3 the day it opens?
We are testing the rental flow with a small group first. Leave an email and we will tell you when Mistral 7B v0.3 is ready to run. One message, no newsletter.
Mistral 7B v0.3 questions
Do I need to install anything to use Mistral 7B v0.3?
No. We start a machine with Mistral 7B v0.3 already loaded and hand you a link. Everything runs in your browser, there is nothing to download, and nothing is left on your computer afterwards. It works the same on a Mac, a Windows laptop, or a Chromebook. A workspace is usually ready in about 90 seconds.
How much does it cost to run 1,000 training examples?
About $0.26. Mistral 7B v0.3 takes about 2 seconds per example on the RTX 4090 we recommend, so 1,000 training examples is roughly 35 minutes of GPU time at $0.45 per hour. Billing is by the minute, and a batch job shuts the GPU off the moment the last item finishes. The calculator above works this out for your own numbers.
Can I run Mistral 7B v0.3 on a cheaper card?
Sometimes, and the calculator will not always make it look worth it. Same reasoning as Llama 3.1 8B. LoRA training on a 7 billion parameter model needs about 15GB with a reasonable batch size, and a 24GB card covers that with headroom for longer training examples. Going larger buys you a bigger batch size and a modestly shorter run, which does not pay for itself at this scale. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.
Can I use Mistral 7B v0.3 commercially?
Yes. Mistral 7B v0.3 is released under the Apache 2.0 license, which permits commercial use with no conditions worth worrying about. You can use the output in paid client work and in products you sell.
What happens to my files after I stop?
Anything you save into your workspace folder stays in your account and is there when you come back. Everything else is destroyed: the machine is terminated and its disk is wiped. Batch job inputs and outputs are deleted from our storage 24 hours after you download them. We do not read your files or use them to train anything.
What if it fails partway through?
You are not charged for work that did not complete, and failed sessions are refunded automatically. Batch jobs write each output as it finishes rather than at the end, so a failure at item 380 of 400 leaves you 379 usable files and a message saying what broke. Restarting picks up where it stopped rather than redoing the work.
Own a GPU that sits idle? Put it to work. The average provider earns $180 to $420 per month per card.
List your GPU