Llama 3.2 3B Instruct
Open weightMeta · Released September 2024 · Knowledge cutoff December 2023
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.
It belongs to Meta's open-weight Llama family: Llama 4 Maverick is the capability lead, Scout the efficient long-context sibling, Llama Guard the safety classifier, and the 3.x line remains a dependable workhorse.
Facts and pricing
- Provider
- Meta
- Context window
- 80K tokens
- Input price
- 0.61 credits / 1M tokens ($0.051 raw)
- Output price
- 4.0 credits / 1M tokens ($0.34 raw)
- Vision (image input)
- No
- Tool calling
- No
- Extended reasoning
- No
Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.
Try Llama 3.2 3B Instruct now
What Llama 3.2 3B Instruct is best for
- Everyday chat and drafting on an open-weight model with transparent lineage
Example prompts
Prompts that suit a open weight model like Llama 3.2 3B Instruct:
- Draft a project update from these rough notes
- Explain how HTTPS works to a curious teenager
- Turn this list of features into a changelog entry
- Brainstorm objections to this proposal and how to answer them
Meta family
| Model | Context | Input cr/M | Output cr/M | Released |
|---|---|---|---|---|
| Llama Guard 4 12B | 164K | 2.2 | 2.2 | April 2025 |
| Llama 4 Maverick | 128K | 2.2 | 7.8 | April 2025 |
| Llama 4 Scout | 328K | 1.2 | 3.6 | April 2025 |
| Llama 3.3 70B Instruct | 131K | 1.2 | 3.8 | December 2024 |
| Llama 3.2 1B Instruct | 60K | 0.32 | 2.4 | September 2024 |
| Llama 3.2 3B Instruct | 80K | 0.61 | 4.0 | September 2024 |
| Llama 3.1 8B Instruct | 131K | 0.60 | 0.96 | July 2024 |
| Llama 3.1 70B Instruct | 131K | 8.6 | 8.6 | July 2024 |
Model comparisons
- Llama 4 Maverick vs DeepSeek V4 Pro 0423
- Llama 4 Maverick vs Qwen3.7 Max
- Llama 4 Maverick vs Mistral Medium 3.5
- Llama 4 Scout vs Gemini 3.5 Flash
Frequently asked questions
- What is Llama 3.2 3B Instruct?
- Llama 3.2 3B Instruct is an AI model by Meta. 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.
- How much does Llama 3.2 3B Instruct cost on Zeplik?
- Input tokens cost 0.61 credits per million and output tokens 4.0 credits per million (1 credit = $0.10; the raw provider rates are $0.051 and $0.34 per million). New accounts start with free credits.
- How long can a conversation with Llama 3.2 3B Instruct be?
- Llama 3.2 3B Instruct has a 80K-token context window (80,000 tokens), which covers the conversation plus any documents you attach.
- Does Llama 3.2 3B Instruct support images and tools?
- Llama 3.2 3B Instruct is text-only and does not support tool calling.
Related models
Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification.
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis.
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient.
More you can do with Llama 3.2 3B Instruct
- 468 AI skillsReady-to-run expert methods for writing, data, code and more, each running on Llama 3.2 3B Instruct or any model you pick.
- 997 integrationsConnect Gmail, Slack, GitHub, Notion and hundreds more so the assistant can work in your apps.
- Simple pricingPlus, Pro and Max plans with a monthly credit allowance that works across every model.