MetaReleased on Sep 25, 2024

Llama 3.2 90B Instruct: Benchmarks, Pricing & Size

Llama 3.2 90B Instruct is a language model from Meta, released in September 2024, with multimodal input.

Llama 3.2 90B is a large multimodal language model optimized for visual recognition, image reasoning, and captioning tasks. It supports a context length of 128,000 tokens and is designed for deployment on edge and mobile devices, offering

Input
TextImage
Output
Text
Speed
Latency p95500ms
Throughput P95100char/s
Cost
$0.36/ 1M · 8:1 in:out
$0.35 in · $0.40 out

Llama 3.2 90B Instruct pricing

Providers

Llama 3.2 90B Instruct starts at $0.350 per million input tokens and $0.400 per million output tokens via DeepInfra. See all 5 providers below with their per-token pricing, latency, throughput, and modality support.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
DeepInfra logoDeepInfra
$0.350$0.400128.0K128.0K
0.50
24 c/s
—
Bedrock logoBedrock
$0.720$0.720128.0K128.0K
0.50
100 c/s
—
Fireworks logoFireworks
$0.890$0.890128.0K128.0K
0.50
50 c/s
—
Together logoTogether
$1.20$1.20128.0K128.0K
0.50
57 c/s
—
Hyperbolic logoHyperbolic
$2.00$2.00128.0K128.0K
0.50
42 c/s
—
Loading chart...
Loading chart...
Loading chart...

Llama 3.2 90B Instruct model size

Llama 3.2 90B Instruct has 90 billion parameters. See how it compares to other models in the same parameter range.

Parameters
90B
Very large (80–200B)
90B
1B7B70B405B

Llama 3.2 90B Instruct API

API access coming soon

Llama 3.2 90B Instruct will be available through our gateway shortly.

Llama 3.2 90B Instruct examples

Recent arena outputs from Llama 3.2 90B Instruct, picked from the highest-ranked matchups.

Llama 3.2 90B Instruct license

Llama 3.2 90B Instruct is released under the Llama 3.2 license, which permits commercial use, has 90.0B parameters.

License
Llama 3.2
Commercial use allowed
Parameters
90.0B

Meta Llama 3.2 Community License

FAQ

Common questions about Llama 3.2 90B Instruct.

When was Llama 3.2 90B Instruct released?

Llama 3.2 90B Instruct was released on September 25, 2024 by Meta. This is the official Llama 3.2 90B Instruct release date tracked on LLM Stats.

Is Llama 3.2 90B Instruct available via API?

Yes, Llama 3.2 90B Instruct is available via API. See the official documentation for authentication and endpoint details. It is served by 5 providers tracked on LLM Stats.

How big is Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct has 90 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct was created by Meta.

What is the license for Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct is released under the Llama 3.2 license. This is an open-source / open-weight license that permits self-hosting.

Is Llama 3.2 90B Instruct multimodal?

Yes, Llama 3.2 90B Instruct is multimodal and can accept both text and images as input.

Where can I use Llama 3.2 90B Instruct?

Llama 3.2 90B Instruct is available through 5 providers including DeepInfra, Bedrock, Fireworks, and 2 more.

Where is the Llama 3.2 90B Instruct paper or technical report?

Llama 3.2 90B 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.