Llama 3.1 Nemotron Nano 4B v1.1

About

Compact 4B parameter NVIDIA Nemotron Nano model for edge inference.

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 3.1 Nemotron Nano 4B v1.1 vs Qwen2 7B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs ShieldGemma 9B Llama 3.1 Nemotron Nano 4B v1.1 vs Dracarys Llama 3.1 70B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Gemma 2 9B SahabatAI Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Llama 3 Taiwan 70B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Llama 3 Swallow 70B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Llama 3.1 Swallow 8B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Bielik 11B v2.6 Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Sarvam-M Multilingual Hybrid Llama 3.1 Nemotron Nano 4B v1.1 vs Teuken 7B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Italia 10B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Colosseum 355B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Stockmark 2 100B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Seed-OSS 36B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Marin 8B Instruct Llama 3.1 Nemotron Nano 4B v1.1 vs Granite Guardian 3.0 8B

Specifications

FamilyNemotron Nano 2

Released2025-04-01

Parameters4B

Context4K

ArchitectureDecoder Only

Specializationgeneral

Trainingpretraining

Fine-tuninginstruction_tuning

Providers(1)