LLM EXPLORER 55,709 MODELS INDEXED

Nemotron H 47B Base 8K by nvidia

By nvidia · 274 downloads
HF Repo ↗ Copy URL

Nemotron H 47B Base 8K is an open-source language model by nvidia. Features: 56b LLM, VRAM: 93.5GB, Context: 8K, License: other, LLM Explorer Score: 0.18.

  Arxiv:2504.03624 Base model:finetune:nvidia/nem... Base model:nvidia/nemotron-h-5...   De   En   Endpoints compatible   Es   Ext 8k   Fr   It   Jp   Ko   Nemotron-h   Nvidia   Pt   Pytorch   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K 

Nemotron H 47B Base 8K Parameters and Internals

LLM NameNemotron H 47B Base 8K
Repository 🤗https://huggingface.co/nvidia/Nemotron-H-47B-Base-8K 
Base Model(s)  Nemotron H 56B Base 8K   nvidia/Nemotron-H-56B-Base-8K
Model Size56b
Required VRAM93.5 GB
Updated2026-07-25
Maintainernvidia
Model Typenemotron_h
Model Files  4.9 GB: 1-of-20   4.8 GB: 2-of-20   4.6 GB: 3-of-20   4.6 GB: 4-of-20   4.9 GB: 5-of-20   4.5 GB: 6-of-20   4.9 GB: 7-of-20   4.8 GB: 8-of-20   4.9 GB: 9-of-20   4.8 GB: 10-of-20   4.9 GB: 11-of-20   4.8 GB: 12-of-20   4.9 GB: 13-of-20   4.5 GB: 14-of-20   4.8 GB: 15-of-20   4.8 GB: 16-of-20   4.6 GB: 17-of-20   4.8 GB: 18-of-20   4.6 GB: 19-of-20   3.1 GB: 20-of-20
Supported Languagesen de es fr it ko pt ru jp zh
Context Length8k
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.48.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Nemotron H 47B Base 8K

Best Alternatives
Context / RAM
Downloads
Likes
Nemotron H 56B Base 8K8K / 112.4 GB1006933
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Nemotron-H-47B-Base-8K.