LLM EXPLORER 58,975 MODELS INDEXED

NVIDIA Nemotron Labs Teacher Instruction Following by nvidia

By nvidia · 891 downloads
HF Repo ↗ Copy URL

NVIDIA Nemotron Labs Teacher Instruction Following is an open-source language model by nvidia. Features: 560.5b LLM, VRAM: 214.9GB, Context: 256K, License: other, Instruction-Based.

  Ar   Conversational   Custom code Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   En   Endpoints compatible   Es   Fr   He   Hi   Instruct   It   Ja   Ko   Latent-moe   Mtp   Nemotron-3   Nemotron h   Nvidia   Pt   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Teacher-Instruction-Following 

NVIDIA Nemotron Labs Teacher Instruction Following Parameters and Internals

LLM NameNVIDIA Nemotron Labs Teacher Instruction Following
Repository 🤗https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Teacher-Instruction-Following 
Model Size560.5b
Required VRAM214.9 GB
Updated2026-08-20
Maintainernvidia
Model Typenemotron_h
Instruction-BasedYes
Model Files  5.0 GB: 1-of-225   5.0 GB: 2-of-225   5.0 GB: 3-of-225   5.0 GB: 4-of-225   4.9 GB: 5-of-225   5.0 GB: 6-of-225   5.0 GB: 7-of-225   5.0 GB: 8-of-225   5.0 GB: 9-of-225   5.0 GB: 10-of-225   5.0 GB: 11-of-225   5.0 GB: 12-of-225   5.0 GB: 13-of-225   5.0 GB: 14-of-225   5.0 GB: 15-of-225   5.0 GB: 16-of-225   5.0 GB: 17-of-225   5.0 GB: 18-of-225   5.0 GB: 19-of-225   5.0 GB: 20-of-225   5.0 GB: 21-of-225   5.0 GB: 22-of-225   5.0 GB: 23-of-225   5.0 GB: 24-of-225   5.0 GB: 25-of-225   5.0 GB: 26-of-225   5.0 GB: 27-of-225   5.0 GB: 28-of-225   5.0 GB: 29-of-225   5.0 GB: 30-of-225   5.0 GB: 31-of-225   5.0 GB: 32-of-225   5.0 GB: 33-of-225   5.0 GB: 34-of-225   5.0 GB: 35-of-225   5.0 GB: 36-of-225   5.0 GB: 37-of-225   5.0 GB: 38-of-225   5.0 GB: 39-of-225   5.0 GB: 40-of-225   5.0 GB: 41-of-225   5.0 GB: 42-of-225   5.0 GB: 43-of-225
Supported Languagesen fr es it de pt ja ko hi ar zh he
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Vocabulary Size131072