llama-3.2-3b-instruct

completions

bydeepinfra

llama-3.2-3b-instruct

completions

Published by: meta-llamaProvider:

deepinfra

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 card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/MODEL_CARD.md). Usage of this model is subject to [Meta's Acceptable Use Policy](https://www.llama.com/llama3/use-policy/).

Released

Sep 25, 2024

Knowledge

Mar 29, 2024

License

llama_3_2_community_license

Context

131072

Input

$0.01 / 1M tokens

Output

$0.02 / 1M tokens

Accepts: text

Returns: text

Released Sep 25, 2024Knowledge Cutoff: Mar 29, 2024License: llama_3_2_community_license

Context: 131072 Input: $0.01 / 1M tokensOutput: $0.02 / 1M tokensAccepts: textReturns: text

Access llama-3.2-3b-instruct through LangDB AI Gateway

Recommended

Integrate with meta-llama's llama-3.2-3b-instruct and 250+ other models through a unified API. Monitor usage, control costs, and enhance security.

Unified API

Cost Optimization

Enterprise Security

Get Started Now

Free tier available • No credit card required

Instant Setup

99.9% Uptime

10,000+Monthly Requests

Benchmark Results for llama-3.2-3b-instruct

Category Performance Scores:

Academia: Score 22.00 (Top 85% - Rank #276)
Finance: Score 19.50 (Top 82% - Rank #266)
Marketing: Score 30.88 (Top 48% - Rank #156)
Maths: Score 27.80 (Top 82% - Rank #266)
Programming: Score 6.70 (Top 93% - Rank #302)
Science: Score 32.80 (Top 87% - Rank #282)
Writing: Score 24.49 (Top 50% - Rank #162)

Overall Performance: 23.452857142857145 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
AIME	6.70	Top 71%	Mathematics
AA Coding Index	6.70	Top 93%	Programming
AAII	11.20	Top 86%	General
AA Math Index	27.80	Top 82%	Mathematics
GPQA	32.80	Top 87%	STEM (Physics, Chemistry, Biology)
HLE	5.20	Top 31%	General Knowledge
LiveCodeBench	8.30	Top 91%	Programming
MATH-500	48.90	Top 86%	Mathematics
MMLU	63.40	Top 98%	General Knowledge
MMLU-Pro	34.70	Top 94%	General Knowledge
SciCode	5.20	Top 93%	Scientific

MMLU Score: 63.40 - Massive Multitask Language Understanding benchmark

GPQA Score: 32.80 - Graduate-level reasoning benchmark

Model Comparison:

Provider: deepinfra

Model Type: completions

Context Size: 131072 tokens

Comparing against 324 models in the database

Performance Analytics for llama-3.2-3b-instruct

Usage Statistics (Last 1 Days):

Total Requests: 1 API calls
Average TPS: 999.74 tokens per second
Average Response Time: 3252.80ms
Average Time to First Token: 312.00ms
Total Cost: $0.00
Average Request Cost: $0.0001

Daily Performance Breakdown:

Date	Requests	TPS	Response Time	TTFT	Cost
9/10/2025	1	999.74	3252.80ms	312.00ms	$0.00

Performance Summary:

Model: llama-3.2-3b-instruct by deepinfra

Monitoring Period: 9/4/2025 to 9/11/2025

Average Daily Requests: 1

Peak Daily Requests: 1

Statistics

View Full Statistics

Request Volume

Daily API requests

Performance (TPS)

Tokens per second

999.74 tokens/s

Category Scores

Benchmark Tests

View Other Benchmarks

AIME

6.7

Mathematics

AA Coding Index

6.7

Programming

AAII

11.2

General

AA Math Index

27.8

Mathematics

GPQA

32.8

STEM (Physics, Chemistry, Biology)

HLE

5.2

General Knowledge

LiveCodeBench

8.3

Programming

MATH-500

48.9

Mathematics

MMLU

63.4

General Knowledge

MMLU-Pro

34.7

General Knowledge

SciCode

5.2

Scientific

Metric	AIME	AA Coding Index	AAII	AA Math Index	GPQA	HLE	LiveCodeBench	MATH-500	MMLU	MMLU-Pro	SciCode
Score	6.7	6.7	11.2	27.8	32.8	5.2	8.3	48.9	63.4	34.7	5.2

Compare with Similar Models

gemini-2.5-pro-preview

grok-4

Code Examples

Integration samples and API usage

Code Samples for llama-3.2-3b-instruct

Python SDK Example:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    api_key="<your_api_key>"
)

response = client.chat.completions.create(
    model="llama-3.2-3b-instruct",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ]
)

print(response.choices[0].message.content)

TypeScript SDK Example:

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: "https://api.us-east-1.langdb.ai/projects/<your_project_id>",
    apiKey: "<your_api_key>"
});

const response = await client.chat.completions.create({
    model: "llama-3.2-3b-instruct",
    messages: [
        { role: "user", content: "Hello, how are you?" }
    ]
});

console.log(response.choices[0].message.content);

cURL Example:

curl -X POST "https://api.us-east-1.langdb.ai/projects/<your_project_id>/v1/chat/completions" \
  -H "Authorization: Bearer <your_api_key>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3.2-3b-instruct",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: llama-3.2-3b-instruct

Provider: deepinfra

API Endpoint: $https://api.us-east-1.langdb.ai

Create API Key

Related Models

Similar models from deepinfra

llama-3.2-3b-instruct

llama-3.2-3b-instruct

Access llama-3.2-3b-instruct through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B

llama-3.2-3b-instruct by deepinfra - AI Model Details, Pricing, and Performance Metrics

llama-3.2-3b-instruct

llama-3.2-3b-instruct

Access llama-3.2-3b-instruct through LangDB AI Gateway

Statistics

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

deepseek-chat-v3-0324

deepseek-chat-v3.1

deepseek-prover-v2

DeepSeek-R1

deepseek-r1-0528

DeepSeek-R1-Distill-Llama-70B