Skip to content
AI Model Radar

Llama 3.2 3B Instruct

meta-llama/Llama-3.2-3B-Instruct
Open Source · chat · open-weights
Open Alert me on changes
Intelligence
5.7
Context
128K
Max output
—
Weights
Open
API $/1M
$0.03 / $0.05
Modalities
text
Released
18 Sept 2024
Intelligence Index via Artificial Analysis · 0–100, higher is better
License: llama3.2 · meta-llama/Llama-3.2-3B-Instruct
Download image Share on X Share on LinkedIn
AI summary
● machine-written

Llama 3.2 3B Instruct: Open-weights 3B chat model

Llama 3.2 3B Instruct is a 3-billion-parameter open-weights instruction-tuned model developed by Meta, released September 2024. It supports text input/output with a 128K token context window and knowledge cutoff of December 2023. The model is available from multiple providers at competitive pricing starting from $0.030 per million input tokens.

What's new
  • Released September 25, 2024
  • Supports 128K token context window
  • Available from 6 API providers
  • Open-weights model under Llama 3.2 Community License
Best for
Dialogue generation and conversational AINatural language understanding tasksReasoning and summarization workloadsCost-efficient deployment at edge/local
Sources

Source: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct