Llama Embed Nemotron 8B

llama

Nvidia · nvidia/llama-embed-nemotron-8b

Capabilities

Tool CallNo

ReasoningNo

Structured OutputNo

Temperature ControlNo

AttachmentsNo

Open WeightsNo

Input

text

Output

text

Input$0.000

Output$0.000

Direct installation coming soon — March 2026

ProviderNvidia

Model IDnvidia/llama-embed-nemotron-8b

Familyllama

Knowledge Cutoff2025-03

Release Date2025-03-18

Last Updated2025-03-18

Context33K

Max Output2K

@ai-sdk/openai-compatible