Llama 3.2 NV EmbedQA 1B v1 on NVIDIA NIM

NV-Embed · NVIDIA AI

Serverless
Open Weights

Last refreshed 2026-10-21. Next refresh: weekly.

Why use Llama 3.2 NV EmbedQA 1B v1 on NVIDIA NIM?

NVIDIA NIM offers Llama 3.2 NV EmbedQA 1B v1. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: nvidia/llama-3.2-nv-embedqa-1b-v1
Model ID
nvidia/llama-3.2-nv-embedqa-1b-v1

Request example

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID nvidia/llama-3.2-nv-embedqa-1b-v1.

Gotchas

  • Use provider model ID "nvidia/llama-3.2-nv-embedqa-1b-v1", not the LLMReference slug "llama-3.2-nv-embedqa-1b-v1".

Capabilities

No model capability flags are currently sourced.

About Llama 3.2 NV EmbedQA 1B v1

NVIDIA multilingual embedding model for question-answering retrieval, based on Llama 3.2. Outputs 2048-dimensional embeddings and supports 26 languages with 512-token context. Superseded by v2, which extends context to 4K tokens.

Get Started

Model CardDocsPortalPricing

Model Specs

Released2024-10-08
Parameters1B
Context512
ArchitectureEncoder Only

Related Models on NVIDIA NIM

NV-EmbedCode 7B v1Llama 3.2 NV EmbedQA 1B v2Llama 3.2 NV RerankQA 1B v2

Provider

NVIDIA NIM

NVIDIA

All models on NVIDIA NIM →Provider setup guide →