Llama 3.2 3B Instruct: pricing, context and benchmarks

What you need to know about Llama 3.2 3B Instruct

Meta, based in United States, put Llama 3.2 3B Instruct online on September 25, 2024. It accepts text as input and produces text. Its context window reaches 131,072 tokens, larger than 29 % of the models in the registry, and it can write up to 72,000 tokens in one go.

Released more than 2 years ago, it belongs to a generation most vendors have since superseded.

Llama 3.2 3B Instruct pricing

On OpenRouter, Llama 3.2 3B Instruct costs $0.05 per million input tokens and $0.34 per million output tokens. Counting three tokens read for every token written, its average price is $0.122 per million, more expensive than 11 % of paid models (6.3 times cheaper than the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0003. At 1,000 tasks a day, budget $8 a month. The price calculator redoes this with your own volumes.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Llama 3.2 3B Instruct. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It does not support tool calling: it is not suited to driving an AI agent that has to act.
• It can answer in an enforced JSON format (structured outputs).
• Its knowledge stops at December 2023.

Its weights are open and downloadable from Hugging Face (llama3.2 licence): you can run it on your own machines without sending your data to a third party. With 3,212,749,824 billion parameters, it needs about 1,795,263,863 GB of memory at 4-bit quantisation. Check with the VRAM calculator. It was downloaded 1,120,299 times on Hugging Face last month.

Other Meta models