What are the hardware requirements for Nemotron H 47B Reasoning 128K FP8?

Nemotron H 47B Reasoning 128K FP8 requires approximately 49.1 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Nemotron H 47B Reasoning 128K FP8 and how large is it?

Nemotron H 47B Reasoning 128K FP8 is developed by nvidia, a model with 47b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Nemotron H 47B Reasoning 128K FP8?

Nemotron H 47B Reasoning 128K FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Nemotron H 47B Reasoning 128K FP8 by nvidia — VRAM 49.1GB, 128K context

Name: Nemotron H 47B Reasoning 128K FP8
Author: nvidia

Nemotron H 47B Reasoning 128K FP8 is an open-source language model by nvidia. Features: 47b LLM, VRAM: 49.1GB, Context: 128K, License: other, LLM Explorer Score: 0.19.

Arxiv:2504.03624 Arxiv:2505.00949 Conversational En Endpoints compatible Nvidia Pytorch Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/nvidia/Nemotron-H-47B-Reasoning-128K-FP8

Nemotron H 47B Reasoning 128K FP8 Parameters and Internals

LLM Name	Nemotron H 47B Reasoning 128K FP8
Repository 🤗	https://huggingface.co/nvidia/Nemotron-H-47B-Reasoning-128K-FP8
Model Size	47b
Required VRAM	49.1 GB
Updated	2026-08-05
Maintainer	nvidia
Model Type	nemotron_h
Model Files	5.0 GB: 1-of-11 4.7 GB: 2-of-11 4.9 GB: 3-of-11 4.7 GB: 4-of-11 4.9 GB: 5-of-11 4.9 GB: 6-of-11 4.9 GB: 7-of-11 5.0 GB: 8-of-11 4.9 GB: 9-of-11 3.1 GB: 10-of-11 2.1 GB: 11-of-11
Supported Languages	en
Model Architecture	NemotronHForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.51.3
Tokenizer Class	PreTrainedTokenizerFast
Vocabulary Size	131072
Torch Data Type	bfloat16

Rank the Nemotron H 47B Reasoning 128K FP8 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Nemotron H 47B Reasoning 128K FP8

Best Alternatives	Context / RAM	Downloads	Likes
Nemotron H 47B Reasoning 128K	128K / 93.5 GB	279	22

Note: green Score (e.g. "73.2") means that the model is better than nvidia/Nemotron-H-47B-Reasoning-128K-FP8.