Llama 3.2 3B Instruct
Summary
Llama 3.2 3B Instruct is an open-weight language model from Meta, released on 25 Sept 2024. It accepts text and generates text, with a 131K-token context window and up to 72K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.05 per million input tokens and $0.34 per million output tokens (OpenRouter), across 1 provider we track. It is scheduled for retirement on 20 Nov 2026.
Open Llama instruction model for multilingual chat, reasoning, and coding
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Meta |
|---|---|
| Release date | 25 Sept 2024 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | llama3.2 [Hugging Face] |
| Parameters | 3.2B [Hugging Face] |
| Context window | 131K (131,072 tokens) [models.dev] |
| Max output | 72K tokens [models.dev] |
| Knowledge cutoff | Dec 2023 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
| Structured output | Yes [models.dev] |
| Retirement date | 20 Nov 2026 [OpenRouter] |
| Hugging Face | meta-llama/Llama-3.2-3B-Instruct [Hugging Face] |
Llama 3.2 3B Instruct API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter meta-llama/llama-3.2-3b-instruct | $0.05 | $0.34 | – | 80K | OpenRouter, 18 Nov 2026 |
Running Llama 3.2 3B Instruct locally
Estimated memory, from the parameter count on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 1.9 GB | 2.7 GB | – |
| Q8_0 (8-bit) | 3.4 GB | 4.2 GB | – |
| FP16 / BF16 (16-bit) | 6.4 GB | 7.2 GB | – |
At 4-bit with an 8K conversation, Llama 3.2 3B Instruct needs about 2.7 GB, so it fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. The model's architecture is not public, so the conversation cache is not included. Check your own hardware, or see Running local LLMs on an 8 GB GPU on our sister site AIPCs.
Frequently asked questions
What is the context window of Llama 3.2 3B Instruct?
Llama 3.2 3B Instruct has a context window of 131,072 tokens (131K) and can generate up to 72,000 tokens in a single response, according to models.dev.
How much does the Llama 3.2 3B Instruct API cost?
Llama 3.2 3B Instruct is listed from $0.05 per million input tokens and $0.34 per million output tokens (OpenRouter). Prices last verified 18 Nov 2026.
Is Llama 3.2 3B Instruct open source?
Llama 3.2 3B Instruct is an open-weight model: its weights are published on Hugging Face as meta-llama/Llama-3.2-3B-Instruct under the llama3.2 license. Check the license terms before commercial use.
When was Llama 3.2 3B Instruct released?
Meta released Llama 3.2 3B Instruct on 25 Sept 2024, according to models.dev.
How much VRAM does Llama 3.2 3B Instruct need?
About 2.7 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 4.2 GB at 8-bit. The 4-bit model fits on a graphics card with 8 GB or more, such as the NVIDIA GeForce RTX 4060 8 GB. These are estimates from the model's published parameter count.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Phi-4-mini | Microsoft | 11 Dec 2024 | 128K | $0.07 | $0.30 | Open |
| Qwen2.5-Coder-32B-Instruct | Alibaba (Qwen) | 12 Nov 2024 | 131K | $0.06 | $0.20 | Open |
| Command R | Cohere | 30 Aug 2024 | 128K | $0.15 | $0.60 | Open |
| Mistral Small 3.1 24B | Mistral AI | 17 Mar 2025 | 128K | $0.10 | $0.30 | Open |
| Command R7B | Cohere | 13 Dec 2024 | 128K | $0.04 | $0.15 | Open |
| Gemma 3 27B IT | Google DeepMind | 12 Mar 2025 | 131K | $0.08 | $0.16 | Open |
Change history
- Max output changed from 118K to 72K
- OpenRouter price changed: input $0.05 → $0.05, output $0.33 → $0.34 per 1M tokens
- Tool calling changed from yes to no
- Structured output changed from no to yes
- Max output changed from 4K to 118K
- Name changed from Llama 3.2 3B to Llama 3.2 3B Instruct
- Context window changed from 128K to 131K
- No longer listed on OpenRouter
- Tool calling changed from no to yes
- Name changed from Llama 3.2 3B Instruct to Llama 3.2 3B
- Context window changed from 80K to 128K
- Max output changed from 80K to 4K
- No longer listed on cloudflare-workers-ai
- OpenRouter price changed: input $0.05 → $0.05, output $0.34 → $0.33 per 1M tokens
- Retirement date changed from 15 Nov 2026 to 20 Nov 2026
- Retirement date changed from none to 15 Nov 2026
- OpenRouter price changed: input $0.05 → $0.05, output $0.33 → $0.34 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.05, output $0.34 → $0.33 per 1M tokens
- OpenRouter price changed: input $0.05 → $0.05, output $0.33 → $0.34 per 1M tokens