llama3-2-3b-instruct-v1.0

completions

bybedrock

llama3-2-3b-instruct-v1.0

completions

Published by: metaProvider:

bedrock

Text-only lightweight model built to deliver highly accurate and relevant results. Designed for applications requiring low-latency inferencing and limited computational resources. Ideal for query and prompt rewriting, mobile AI-powered writing assistants, and customer service applications, particularly on edge devices where its efficiency and low latency enable seamless integration into various applications, including mobile AI-powered writing assistants and customer service chatbots.

Released

Sep 25, 2024

Knowledge

Mar 29, 2024

License

Meta Llama Community

Context

128K

Input

$0.15 / 1M tokens

Output

$0.15 / 1M tokens

Accepts: text, image

Returns: text

Released Sep 25, 2024Knowledge Cutoff: Mar 29, 2024License: Meta Llama Community

Context: 128K Input: $0.15 / 1M tokensOutput: $0.15 / 1M tokensAccepts: text, imageReturns: text

Access llama3-2-3b-instruct-v1.0 through LangDB AI Gateway

Recommended

Integrate with meta's llama3-2-3b-instruct-v1.0 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 llama3-2-3b-instruct-v1.0

Category Performance Scores:

Maths: Score 3.30 (Top 95% - Rank #304)
Finance: Score 7.25 (Top 98% - Rank #314)
Science: Score 30.47 (Top 96% - Rank #308)
Writing: Score 21.16 (Top 97% - Rank #311)
Academia: Score 22.00 (Top 92% - Rank #295)
Marketing: Score 19.89 (Top 96% - Rank #308)

Overall Performance: 17.347037037037037 average score across all categories

Detailed Benchmark Scores:

Benchmark	Score	Percentile	Domain
HLE	5.20	Top 42%	General Knowledge
AIME	6.70	Top 78%	Mathematics
GPQA	32.80	Top 90%	STEM (Physics, Chemistry, Biology)
MMLU	63.40	Top 96%	General Knowledge
SciCode	5.20	Top 96%	Scientific
MATH-500	48.90	Top 93%	Mathematics
MMLU-Pro	34.70	Top 97%	General Knowledge
LiveCodeBench	8.30	Top 95%	Programming
AA Math Index	3.30	Top 95%	Mathematics
AAII	11.20	Top 93%	General

MMLU Score: 63.40 - Massive Multitask Language Understanding benchmark

GPQA Score: 32.80 - Graduate-level reasoning benchmark

Model Comparison:

Provider: bedrock

Model Type: completions

Context Size: 128000 tokens

Comparing against 320 models in the database

Category Scores

Benchmark Tests

View Other Benchmarks

HLE

5.2

General Knowledge

AIME

6.7

Mathematics

GPQA

32.8

STEM (Physics, Chemistry, Biology)

MMLU

63.4

General Knowledge

SciCode

5.2

Scientific

MATH-500

48.9

Mathematics

MMLU-Pro

34.7

General Knowledge

LiveCodeBench

8.3

Programming

AA Math Index

3.3

Mathematics

AAII

11.2

General

Metric	HLE	AIME	GPQA	MMLU	SciCode	MATH-500	MMLU-Pro	LiveCodeBench	AA Math Index	AAII
Score	5.2	6.7	32.8	63.4	5.2	48.9	34.7	8.3	3.3	11.2

Compare with Similar Models

Code Examples

Integration samples and API usage

Code Samples for llama3-2-3b-instruct-v1.0

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="llama3-2-3b-instruct-v1.0",
    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: "llama3-2-3b-instruct-v1.0",
    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": "llama3-2-3b-instruct-v1.0",
    "messages": [
        {"role": "user", "content": "Hello, how are you?"}
    ]
  }'

Model: llama3-2-3b-instruct-v1.0

Provider: bedrock

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

Create API Key

Related Models

Similar models from bedrock

llama3-2-3b-instruct-v1.0

llama3-2-3b-instruct-v1.0

Access llama3-2-3b-instruct-v1.0 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

mistral-7b-instruct-v0.2

command-r-plus-v1.0

command-r-v1.0

llama3-1-70b-instruct-v1.0

llama3-1-8b-instruct-v1.0

llama3-2-1b-instruct-v1.0

llama3-2-3b-instruct-v1.0 by bedrock - AI Model Details, Pricing, and Performance Metrics

llama3-2-3b-instruct-v1.0

llama3-2-3b-instruct-v1.0

Access llama3-2-3b-instruct-v1.0 through LangDB AI Gateway

Category Scores

Benchmark Tests

Compare with Similar Models

Code Examples

Related Models

mistral-7b-instruct-v0.2

command-r-plus-v1.0

command-r-v1.0

llama3-1-70b-instruct-v1.0

llama3-1-8b-instruct-v1.0

llama3-2-1b-instruct-v1.0