LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 3 1 Nemotron Ultra 253B V1 FP8 by nvidia

 »  All LLMs  »  nvidia  »  Llama 3 1 Nemotron Ultra 253B V1 FP8   URL Share it on

  1216   
  Arxiv:2411.19146   Arxiv:2502.00203   Arxiv:2503.18908   Arxiv:2505.00949   Autotrain compatible   Conversational   Custom code   En   Llama-3   Nemotron-nas   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 

Llama 3 1 Nemotron Ultra 253B V1 FP8 Benchmarks

LLME Score: 0.2486
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 1 Nemotron Ultra 253B V1 FP8 (nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8)
🌟 Advertise your project 🚀

Llama 3 1 Nemotron Ultra 253B V1 FP8 Parameters and Internals

LLM NameLlama 3 1 Nemotron Ultra 253B V1 FP8
Repository 🤗https://huggingface.co/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8 
Model Size253b
Required VRAM198.8 GB
Updated2025-09-23
Maintainernvidia
Model Typenemotron-nas
Model Files  5.0 GB: 1-of-52   4.8 GB: 2-of-52   4.9 GB: 3-of-52   4.9 GB: 4-of-52   4.8 GB: 5-of-52   4.3 GB: 6-of-52   4.9 GB: 7-of-52   4.6 GB: 8-of-52   4.9 GB: 9-of-52   4.6 GB: 10-of-52   5.0 GB: 11-of-52   4.6 GB: 12-of-52   4.9 GB: 13-of-52   4.6 GB: 14-of-52   4.9 GB: 15-of-52   4.6 GB: 16-of-52   4.9 GB: 17-of-52   4.6 GB: 18-of-52   4.9 GB: 19-of-52   4.6 GB: 20-of-52   4.9 GB: 21-of-52   4.6 GB: 22-of-52   4.9 GB: 23-of-52   4.6 GB: 24-of-52   4.8 GB: 25-of-52   5.0 GB: 26-of-52   4.6 GB: 27-of-52   4.9 GB: 28-of-52   4.8 GB: 29-of-52   4.9 GB: 30-of-52   4.5 GB: 31-of-52   4.9 GB: 32-of-52   6.5 GB: 33-of-52   6.5 GB: 34-of-52   6.5 GB: 35-of-52   7.0 GB: 36-of-52   7.0 GB: 37-of-52   7.0 GB: 38-of-52   5.6 GB: 39-of-52
Supported Languagesen
Model ArchitectureDeciLMForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.48.3
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 1 Nemotron Ultra 253B V1 FP8

Best Alternatives
Context / RAM
Downloads
Likes
...ama 3 1 Nemotron Ultra 253B V1128K / 405.3 GB2183331
...3 1 Nemotron Ultra 253B CPT V1128K / 167.6 GB206
... 1 Nemotron Ultra 253B V1 GGUF128K /  GB16859
Note: green Score (e.g. "73.2") means that the model is better than nvidia/Llama-3_1-Nemotron-Ultra-253B-v1-FP8.

Rank the Llama 3 1 Nemotron Ultra 253B V1 FP8 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 51545 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer