Run Llama 3.3 70B

Ready in about 90 seconds. No install, no setup. From $1.35 per hour.

SOC 2 controls 142 verified providers 99.2% uptime Ready in about 90 seconds

What it does

Llama 3.3 70B is a large general-purpose language model. It writes, summarizes, answers questions, extracts information from documents, and follows instructions about as well as the commercial assistants most people already use.

The reason to run it here rather than through an API is privacy. Nothing you type leaves the machine we start for you, and we delete the machine and its disk when you stop.

That matters for legal documents, medical notes, HR files, customer records, and anything covered by a contract that forbids sending data to a third party.

What you can ask it

You give it

Summarise this 40 page supplier contract and list every clause about termination.

You get back

Returns a one page summary plus a clause-by-clause list with page references.

You give it

Read these 200 support emails and tell me the five most common complaints.

You get back

Groups the emails by theme and gives counts and representative quotes for each.

You give it

Rewrite this policy document at a grade 8 reading level.

You get back

Returns the rewritten document, keeping the defined terms intact.

You give it

Pull the invoice number, date, and total from each of these 300 PDFs into a table.

You get back

Returns a CSV with one row per document and flags the ones it was unsure about.

Your setup

WE RUN THIS ON A100 80GB

We run this on an A100 80GB. The whole model fits in memory in its 4-bit form with room for a long document, and it writes at about 40 words per second. $1.35 per hour, billed by the minute.

Why this card?

Seventy billion parameters is about 140GB at full precision and about 40GB compressed to 4-bit. The compressed version fits on an 80GB card with roughly 40GB left over, and that leftover memory is what holds the conversation and any documents you paste in. Squeezing it onto a 48GB card works until you paste a long document, at which point it runs out of room mid-answer.

Memory
80GB
Speed
about 34 seconds per thousand words
Rate
$1.35/hr

What will it cost you?

100 thousand words written 57 minutes $1.28

Billed by the minute on a A100 80GB at $1.35 per hour. A batch job shuts the GPU off when the last thousand words is done, so this is the whole cost.

Two ways to run it

OPEN THE APP

Click and use it

Open WebUI in your browser. It looks and works like a normal chat window, and you can upload documents into the conversation.

Get early access Best for exploring.
RUN A BATCH JOB

Hand us the whole pile

Send a spreadsheet where each row is a task. We run all of them and return the answers in a new column.

Join the list Best for volume. The GPU shuts off automatically when it is done.
1,502 Llama 3.3 70B jobs run on GPUVault in the last 30 days
Model facts
Parameters70B
LicenseLlama 3.3 Community License
Memory required48GB minimum (4-bit), 80GB recommended
Base modelTrained from scratch by Meta
PublisherMeta
Recommended hardwareA100 80GB, 80GB
Hugging Facemeta-llama/Llama-3.3-70B-Instruct
COMING SOON

Want Llama 3.3 70B the day it opens?

We are testing the rental flow with a small group first. Leave an email and we will tell you when Llama 3.3 70B is ready to run. One message, no newsletter.

Llama 3.3 70B questions

Is running Llama 3.3 here actually private?

Your session runs on one machine, reachable only through a link tied to your account. We do not read the contents of your session, and the disk is wiped when the session ends. One caveat: the machine belongs to a verified provider in our network, not to us. For regulated data, read our security page and talk to us about a dedicated instance before you start.

Can I use Llama 3.3 in a commercial product?

Yes, with one condition. The Llama 3.3 Community License permits commercial use unless your product had more than 700 million monthly active users on the day Llama 3.3 was released. Almost no company crosses that line. You also have to display "Built with Llama" if you build a product on top of it.

Do I need to install anything to use Llama 3.3 70B?

No. We start a machine with Llama 3.3 70B 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 100 thousand words written?

About $1.28. Llama 3.3 70B takes about 34 seconds per thousand words on the A100 80GB we recommend, so 100 thousand words written is roughly 57 minutes of GPU time at $1.35 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 Llama 3.3 70B on a cheaper card?

Sometimes, and the calculator will not always make it look worth it. Seventy billion parameters is about 140GB at full precision and about 40GB compressed to 4-bit. The compressed version fits on an 80GB card with roughly 40GB left over, and that leftover memory is what holds the conversation and any documents you paste in. Squeezing it onto a 48GB card works until you paste a long document, at which point it runs out of room mid-answer. If you want to try a different card anyway, the advanced catalog lets you pick one and shows the estimated time before you commit.

What are the license restrictions on Llama 3.3 70B?

Llama 3.3 70B is released under the Llama 3.3 Community License. That is not a permissive license, so read it before you use the output in paid work. We show the license on every model page precisely because this catches people out, and there is usually a permissively licensed alternative in the same category.

Own a GPU that sits idle? Put it to work. The average provider earns $180 to $420 per month per card.

List your GPU