Can I run Llama 3.2 3B locally?

Yes, the weights are open and available on Hugging Face under Meta's Acceptable Use Policy. A model this size runs on modest consumer hardware; tools like Ollama or LM Studio are the easiest way to get it running on your own machine.

What does it cost and how long is the context?

Via API it is priced at $0.05 per million input tokens and $0.33 per million output tokens, making it one of the cheaper options available. The context window is 131,072 tokens.

How does the 3B compare to the larger Llama 3.2 models?

The 3B is the smallest instruct variant in the Llama 3.2 line, trading raw reasoning depth for speed, low cost, and the ability to run on limited hardware. If your task demands heavy multi-step reasoning or long-form generation quality, the larger siblings will serve you better.

Llama 3.2 3B Instruct

6370°

#llm #meta-llama #chat #multilingual #summarization #local

Run this model

Offers / Ads

OpenRouter Terminal / API

Pay per token

Chat with this model in the browser or call it from your code with one API key.

Meta | 131,072 token context | $0.05/M input, $0.33/M output. Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages. Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings. Click here for the original model cardOpens in new tab. Usage of this model is subject to Meta's Acceptable Use PolicyOpens in new tab.

Guides for this model

Ollama vs LM Studio (2026): which local AI app to use, and which top models each one runs

Best local LLM by use case (October 2026): the right open model for every job

How much VRAM do I actually need for local AI?

What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)

All guides

Captain's notes

Written by Captain, the house editor

Notes from 2026-10-13

Llama 3.2 3B Instruct is Meta's compact multilingual model, trained on 9 trillion tokens and tuned for instruction-following, dialogue, and tool use across eight languages. At 3 billion parameters it runs comfortably on modest hardware, and the weights are open. If you need a capable small model you can deploy locally or call via API for near-nothing, this is a serious option.

Known for

Runs locally on low-end hardware thanks to its 3B parameter count
Supports eight languages including English, Spanish, and Hindi out of the box
Strong instruction-following and tool use for its size class
131,072-token context window, unusually large for a model this small
API pricing is among the cheapest available for a capable instruct model

Watch out for

Open weights come under Meta's Acceptable Use Policy, not a fully permissive licence — check it before deploying commercially.
At 3B parameters, complex multi-step reasoning will hit a ceiling that larger models clear more easily.
Multilingual support covers eight named languages; anything outside that list is untested territory.

Best for

Prompts to try

Multilingual customer reply

A customer has written: 'Hola, hice un pedido hace dos semanas y todavía no ha llegado. ¿Pueden ayudarme?' Draft a polite, helpful reply in Spanish that apologises, asks for their order number, and explains the next steps for tracking a delayed shipment.

Summarise a long document

Here is a lengthy company policy document. Summarise it in plain English under five bullet points, each no longer than one sentence. Focus on what an employee actually needs to know day-to-day. [Paste your document below this line]

Tool-use planning task

You have access to three tools: web_search, calculator, and send_email. A user asks: 'What is the current population of Brazil, multiply it by 0.03, and email the result to finance@example.com with a one-line explanation.' Write out the exact sequence of tool calls you would make and why.

Compare with

Llama 3.1 70B Instruct
Open-weights model
131,072 token context · $0.40/M input, $0.40/M output
Llama Guard 4 12B
Open-weights model
163,840 token context · $0.18/M input, $0.18/M output
Llama 3.3 70B Instruct
Open-weights model
131,072 token context · $0.10/M input, $0.32/M output
Llama 4 Scout
Open-weights model
1,310,720 token context · $0.18/M input, $0.59/M output

More text models from meta-llama

Questions people ask

Can I run Llama 3.2 3B locally?: Yes, the weights are open and available on Hugging Face under Meta's Acceptable Use Policy. A model this size runs on modest consumer hardware; tools like Ollama or LM Studio are the easiest way to get it running on your own machine.
What does it cost and how long is the context?: Via API it is priced at $0.05 per million input tokens and $0.33 per million output tokens, making it one of the cheaper options available. The context window is 131,072 tokens.
How does the 3B compare to the larger Llama 3.2 models?: The 3B is the smallest instruct variant in the Llama 3.2 line, trading raw reasoning depth for speed, low cost, and the ability to run on limited hardware. If your task demands heavy multi-step reasoning or long-form generation quality, the larger siblings will serve you better.

Captain's verdict
A genuinely useful small model: cheap, locally runnable, multilingual, and honest about what a 3B parameter count can and cannot do.

Model card on Hugging Face

Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Also ranked: #90 Hottest Text / LLM text model

Not this creator?

Get your own badge

How this score adds up

This model has no popularity data from any source yet, so it carries a stand-in number below 7,000° that keeps the lists complete. It never ranks above a model with data. The breakdown appears here as soon as a source reports it.

Glossary: the terms used here

Heat score: One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor: The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
Download-equivalents: Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale: Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes: Thumbs up and likes from every source, worth half a download each on the log scale.
Adoption rate: How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated: Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder: Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde: A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites: Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
Full model (checkpoint): The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding: Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights: The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age: Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost: A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score: A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
Trend: How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model: The middle of the catalog: half the models with a figure grew faster over the period, half slower.

Similar Models

Llama 3.2 1B Instruct

TEXT / LLM

GPT 6 Sol Pro

TEXT / LLM

AI Models for Image, Video & Text Generation

Llama 3.2 3B Instruct is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.

More Text / LLM models llm meta-llama chat multilingual summarization local budget

Browse by Model Family