Nemotron Mini 4B Instruct

About

NVIDIA Nemotron Mini 4B Instruct, a small instruction-tuned model for chat applications.

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 →

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

Specifications

FamilyNemotron-4

Released2024-08-01

Parameters4B

Context4K

ArchitectureDecoder Only

Specializationgeneral

Trainingpretraining

Fine-tuninginstruction_tuning

Providers(1)