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

Nemotron 3 Ultra 550B A55B 4bit by mlx-community

 »  All LLMs  »  mlx-community  »  Nemotron 3 Ultra 550B A55B 4bit   URL Share it on

  433   

Nemotron 3 Ultra 550B A55B 4bit is an open-source language model by mlx-community. Features: 550b LLM, VRAM: 130GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.34.

  4-bit   4bit Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code   Mlx   Nemotron   Nemotron h   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Nemotron-3-Ultra-550B-A55B-4bit 

Nemotron 3 Ultra 550B A55B 4bit Benchmarks

LLME Score: 0.34004
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nemotron 3 Ultra 550B A55B 4bit (mlx-community/Nemotron-3-Ultra-550B-A55B-4bit)
🌟 Advertise your project 🚀

Nemotron 3 Ultra 550B A55B 4bit Parameters and Internals

LLM NameNemotron 3 Ultra 550B A55B 4bit
Repository 🤗https://huggingface.co/mlx-community/Nemotron-3-Ultra-550B-A55B-4bit 
Base Model(s)  ...emotron 3 Ultra 550B A55B BF16   nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Model Size550b
Required VRAM130 GB
Updated2026-06-06
Maintainermlx-community
Model Typenemotron_h
Model Files  3.0 GB: 1-of-109   1.6 GB: 2-of-109   1.7 GB: 3-of-109   1.7 GB: 4-of-109   1.7 GB: 5-of-109   1.7 GB: 6-of-109   1.7 GB: 7-of-109   1.7 GB: 8-of-109   1.7 GB: 9-of-109   1.7 GB: 10-of-109   1.7 GB: 11-of-109   1.7 GB: 12-of-109   3.0 GB: 13-of-109   3.4 GB: 14-of-109   3.4 GB: 15-of-109   3.4 GB: 16-of-109   3.4 GB: 17-of-109   3.4 GB: 18-of-109   3.4 GB: 19-of-109   3.4 GB: 20-of-109   3.4 GB: 21-of-109   3.4 GB: 22-of-109   3.4 GB: 23-of-109   3.4 GB: 24-of-109   3.4 GB: 25-of-109   3.4 GB: 26-of-109   3.4 GB: 27-of-109   3.4 GB: 28-of-109   3.4 GB: 29-of-109   3.4 GB: 30-of-109   3.4 GB: 31-of-109   3.4 GB: 32-of-109   3.4 GB: 33-of-109   3.4 GB: 34-of-109   3.4 GB: 35-of-109   3.4 GB: 36-of-109   3.4 GB: 37-of-109   3.4 GB: 38-of-109   3.4 GB: 39-of-109   3.4 GB: 40-of-109   3.4 GB: 41-of-109   3.4 GB: 42-of-109   3.4 GB: 43-of-109   3.4 GB: 44-of-109
Quantization Type4bit
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version5.3.0
Vocabulary Size131072

Best Alternatives to Nemotron 3 Ultra 550B A55B 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...emotron 3 Ultra 550B A55B GGUF256K /  GB552719
...motron 3 Ultra 550B A55B NVFP4256K / 63.1 GB19650
...emotron 3 Ultra 550B A55B BF16256K / 204.9 GB47285135
...on 3 Ultra 550B A55B Base BF16256K / 209.9 GB55719
...motron 3 Ultra 550B A55B NVFP4256K / 63.1 GB1584
...motron 3 Ultra 550B A55B GenRM256K / 219.9 GB1649
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Nemotron-3-Ultra-550B-A55B-4bit.

Rank the Nemotron 3 Ultra 550B A55B 4bit 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? 54358 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer