Llama 3.2 3B Instruct Official Specifications, Pricing & Benchmarks
Llama 3.2 3B Instruct (llama-3.2-3b-instruct) by Meta, released 2024-09-25, featuring 131,072 context window, 117,964 max output tokens, and Text input.
📋 Llama 3.2 3B Instruct Official API & System Card Specifications
Verified against official Meta developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- llama-3.2-3b-instruct
- Release Date
- 2024-09-25
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- —
- Function Calling & JSON Schema
- 部分支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 131,000 tokens (131K)
- Max Output Tokens
- 117,964 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.05
- Cached Input / 1M
- $ 0.01 -80%
- Output / 1M Tokens
- $ 0.33
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 Llama 3.2 3B Instruct Full Benchmark Scorecard
10 public benchmarks · ranks among 154 models · synced 2026-11-20
🤖 Agents & Tools 2 items
Berkeley Function Calling Leaderboard (BFCL) v2 is a comprehensive benchmark for evaluating large language models' function calling capabilities.
NexusRaven benchmark for evaluating function calling capabilities of large language models in zero-shot scenarios across cybersecurity tools and API interactions.
📐 Math 4 items
Grade School Math 8K, a dataset of 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.
MGSM (Multilingual Grade School Math) is a benchmark of grade-school math problems. Contains 250 grade-school math problems manually translated from the GSM8K dataset into ten typologically diverse languages: Spanish, French, German, Russian, Chinese, Japanese, Thai, Swahili…
MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions.
🧠 Reasoning & Science 3 items
The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities.
A challenging commonsense natural language inference dataset that uses Adversarial Filtering to create questions trivial for humans (>95% accuracy) but difficult for state-of-the-art models, requiring completion of sentence endings based on physical situations and everyday…
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to Llama 3.2 3B Instruct
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is Llama 3.2 3B Instruct open-source or proprietary?
Llama 3.2 3B Instruct (llama-3.2-3b-instruct) is a proprietary commercial model by Meta. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of Llama 3.2 3B Instruct?
Llama 3.2 3B Instruct supports 131K input context and 117,964 max output tokens, priced at $0.05/1M input ($0.01/1M cached) and $0.33/1M output.