Llama 3.2 NV EmbedQA 1B v2

About

NVIDIA embedding model for question-answering retrieval, based on Llama 3.2.

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

Providers(1)

Provider	Input (per 1M)	Output (per 1M)	Type
NVIDIA NIM	—	—	Serverless

Rankings

Best Open Source LLMs Best Small Language Models (SLMs)Cheapest LLM APIs

Compare

All comparisons →

Llama 3.2 NV EmbedQA 1B v2 vs Qwen2 7B Instruct Llama 3.2 NV EmbedQA 1B v2 vs ShieldGemma 9B Llama 3.2 NV EmbedQA 1B v2 vs Dracarys Llama 3.1 70B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Gemma 2 9B SahabatAI Instruct Llama 3.2 NV EmbedQA 1B v2 vs Llama 3 Taiwan 70B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Llama 3 Swallow 70B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Llama 3.1 Swallow 8B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Bielik 11B v2.6 Instruct Llama 3.2 NV EmbedQA 1B v2 vs Sarvam-M Multilingual Hybrid Llama 3.2 NV EmbedQA 1B v2 vs Teuken 7B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Italia 10B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Colosseum 355B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Stockmark 2 100B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Seed-OSS 36B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Marin 8B Instruct Llama 3.2 NV EmbedQA 1B v2 vs Granite Guardian 3.0 8B

Specifications

FamilyNvidia

Released2025-03-01

Parameters1B

Context4K

Architectureencoder

Specializationembeddings

Trainingpretraining

Providers(1)