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

NVIDIA Nemotron 3 Super 120B A12B FP8 by unsloth

 »  All LLMs  »  unsloth  »  NVIDIA Nemotron 3 Super 120B A12B FP8   URL Share it on

  1486   

NVIDIA Nemotron 3 Super 120B A12B FP8 is an open-source language model by unsloth. Features: 120b LLM, VRAM: 128.4GB, Context: 256K, License: other, LLM Explorer Score: 0.43, ELO: 1365.

  Arxiv:2512.20848   Arxiv:2512.20856 Base model:nvidia/nvidia-nemot... Base model:quantized:nvidia/nv...   Conversational   Custom code Dataset:nvidia/nemotron-post-t... Dataset:nvidia/nemotron-pre-tr...   De   En   Endpoints compatible   Es   Fr   It   Ja   Latent-moe   Modelopt   Mtp   Nemotron-3   Nemotron h   Nvidia   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Unsloth   Zh
Model Card on HF 🤗: https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 

NVIDIA Nemotron 3 Super 120B A12B FP8 Benchmarks

LMSys ELO: 1365 vs 1272 (so35)7.3%
LLME Score: 0.42677
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NVIDIA Nemotron 3 Super 120B A12B FP8 (unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-FP8)
🌟 Advertise your project 🚀

NVIDIA Nemotron 3 Super 120B A12B FP8 Parameters and Internals

LLM NameNVIDIA Nemotron 3 Super 120B A12B FP8
Repository 🤗https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 
Base Model(s)  ...emotron 3 Super 120B A12B BF16   nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
Model Size120b
Required VRAM128.4 GB
Updated2026-05-08
Maintainerunsloth
Model Typenemotron_h
Model Files  5.0 GB: 1-of-26   5.0 GB: 2-of-26   5.0 GB: 3-of-26   5.0 GB: 4-of-26   5.0 GB: 5-of-26   5.0 GB: 6-of-26   5.0 GB: 7-of-26   5.0 GB: 8-of-26   5.0 GB: 9-of-26   5.0 GB: 10-of-26   5.0 GB: 11-of-26   5.0 GB: 12-of-26   5.0 GB: 13-of-26   5.0 GB: 14-of-26   5.0 GB: 15-of-26   5.0 GB: 16-of-26   5.0 GB: 17-of-26   5.0 GB: 18-of-26   5.0 GB: 19-of-26   5.0 GB: 20-of-26   5.0 GB: 21-of-26   5.0 GB: 22-of-26   5.0 GB: 23-of-26   5.0 GB: 24-of-26   5.0 GB: 25-of-26   3.4 GB: 26-of-26
Supported Languagesen fr es it de ja zh
Model ArchitectureNemotronHForCausalLM
Licenseother
Context Length262144
Model Max Length262144
Transformers Version4.57.6
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<SPECIAL_999>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to NVIDIA Nemotron 3 Super 120B A12B FP8

Best Alternatives
Context / RAM
Downloads
Likes
...on 3 Super 120B A12B Base BF161024K / 209.5 GB2267830
...emotron 3 Super 120B A12B BF16256K / 194.6 GB729273344
...motron 3 Super 120B A12B NVFP4256K / 80.3 GB894238290
...Nemotron 3 Super 120B A12B FP8256K / 128.4 GB370440244
...DIA Nemotron 3 Super 120B A12B256K / 214.5 GB17233
...motron 3 Super 120B A12B NVFP4256K / 80.3 GB4608222
... Super 64B A12B Math REAP BF16256K / 128.6 GB6571
...uper 120B A12B BF16 Heretic V2256K / 241.4 GB21903
...20B A12B BF16 REAP 50pct Draft256K / 128.5 GB2046
...emotron 3 Super 120B A12B 5bit256K / 83.1 GB28802
Note: green Score (e.g. "73.2") means that the model is better than unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-FP8.

Rank the NVIDIA Nemotron 3 Super 120B A12B 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? 53640 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