MetaReleased on Sep 25, 2024

Llama 3.2 3B Instruct: Benchmarks, Pricing & Size

Llama 3.2 3B Instruct is a language model from Meta, released in September 2024.

Llama 3.2 3B Instruct is a large language model that supports a context length of 128K tokens and are state-of-the-art in their class for on-device use cases like summarization, instruction following, and rewriting tasks running locally at

Input
Text
Output
Text

Llama 3.2 3B Instruct pricing

Providers

Llama 3.2 3B Instruct starts at $0.0100 per million input tokens and $0.0200 per million output tokens via DeepInfra.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
DeepInfra logoDeepInfra
$0.0100$0.0200128.0K128.0K
0.24
172 c/s

Llama 3.2 3B Instruct model size

Llama 3.2 3B Instruct has 3.2 billion parameters and was trained on 9 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens
3.2B
9Ttokens
2804× tokens-to-params ratio
Small (3–10B)
3.2B
1B7B70B405B

Llama 3.2 3B Instruct API

API access coming soon

Llama 3.2 3B Instruct will be available through our gateway shortly.

Llama 3.2 3B Instruct examples

Recent arena outputs from Llama 3.2 3B Instruct, picked from the highest-ranked matchups.

Llama 3.2 3B Instruct license

Llama 3.2 3B Instruct is released under the Llama 3.2 Community License license, which restricts commercial use, has 3.2B parameters.

License
Llama 3.2 Community License
Non-commercial
Parameters
3.2B

FAQ

Common questions about Llama 3.2 3B Instruct.

When was Llama 3.2 3B Instruct released?

Llama 3.2 3B Instruct was released on September 25, 2024 by Meta. This is the official Llama 3.2 3B Instruct release date tracked on LLM Stats.

Is Llama 3.2 3B Instruct available via API?

Yes, Llama 3.2 3B Instruct is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct has 3.2 billion parameters. It was trained on 9.0 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct was created by Meta.

What is the license for Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct is released under the Llama 3.2 Community License license. This is an open-source / open-weight license that permits self-hosting.

Where can I use Llama 3.2 3B Instruct?

Llama 3.2 3B Instruct is available through 1 provider including DeepInfra.

Where is the Llama 3.2 3B Instruct paper or technical report?

Llama 3.2 3B Instruct has a paper or technical report available at https://ai.meta.com/blog/llama-3-2-connect-2024-vision-edge-mobile-devices/. Use that source for architecture, training, release and evaluation details.