Quick facts

Model ID meta/llama-3.2-3b-instruct

Source Nvidia

Context Window 32768

Pricing -

Capabilities structured output, temperature control, open weights

Model overview

Llama 3.2 3B Instruct is an AI model from Nvidia with 32768 token context window and text input support.

Public token pricing is not listed for this model in the current catalog source.

Model ID meta/llama-3.2-3b-instruct

Provider Nvidia

Family llama

Status -

Knowledge Cutoff -

Release Date 2024-09-18

Input Modalities text

Output Modalities text

Context Window 32768

Input Limit -

Output Limit 32000

Tool Calling No

Reasoning No

Structured Output Yes

Temperature Control Yes

Open Weights Yes

Input Cost / 1M tokens -

Output Cost / 1M tokens -

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -